Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sequences with a consistent symbol pattern interleaved with various words

    oai_token-act-pair · gpt-3.5-turbo

    References to personal experiences and expressions of desire or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.94
     agre
    -0.86
     describ
    -0.76
     mathemat
    -0.75
     streng
    -0.75
     veter
    -0.75
     differe
    -0.73
     exiting
    -0.72
     behaviours
    -0.72
     behaviour
    -0.71
    POSITIVE LOGITS
    Reply
    1.23
    Posts
    1.19
    Topics
    1.18
    ////////////////////////////////
    1.17
    Advertisements
    1.16
    ================================================================
    1.15
    Topic
    1.12
    Spoiler
    1.12
    Pand
    1.11
    --------------------------------
    1.09
    Act Density 0.248%

    No Known Activations