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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" and related phrases indicating possession or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.70
    Ŀ
    -0.65
    UFF
    -0.63
    endish
    -0.60
    NZ
    -0.57
     Tayyip
    -0.57
    leground
    -0.57
    UTC
    -0.56
    noon
    -0.56
    urable
    -0.56
    POSITIVE LOGITS
    'll
    0.89
    'd
    0.78
     SHALL
    0.78
     MUST
    0.73
    ulia
    0.68
    ucci
    0.67
    may
    0.67
     would
    0.65
     SHOULD
    0.63
    aples
    0.63
    Act Density 0.266%

    No Known Activations