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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements starting with "if."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.75
    oscopic
    -0.72
    insula
    -0.65
    Eye
    -0.65
    ãĥŃ
    -0.64
    iliar
    -0.63
     Deity
    -0.62
    emetery
    -0.62
    Rated
    -0.61
    ãĥ¬
    -0.59
    POSITIVE LOGITS
    fy
    0.93
    soever
    0.91
     you
    0.90
     unchecked
    0.86
    rame
    0.77
     we
    0.75
     they
    0.75
    tar
    0.75
    yip
    0.75
     anything
    0.72
    Act Density 0.115%

    No Known Activations