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

    Neuronpedia

    INDEX
    Explanations

    verbs that involve physical or metaphorical penetration or entering

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shake
    -0.62
     differently
    -0.60
     destro
    -0.60
     Caller
    -0.59
     warr
    -0.58
     Brach
    -0.57
     roots
    -0.56
    ById
    -0.56
     bye
    -0.55
    AAAAAAAA
    -0.55
    POSITIVE LOGITS
    strument
    1.99
    clusive
    1.69
    cluded
    1.68
    visible
    1.64
    jured
    1.61
    vasive
    1.53
    jury
    1.53
    iti
    1.52
    jected
    1.48
    flation
    1.46
    Act Density 0.050%

    No Known Activations