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

    Neuronpedia

    INDEX
    Explanations

    words related to being in a state of uncertainty or in-between

    oai_token-act-pair · gpt-3.5-turbo

    terms related to states of uncertainty and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.77
    ructose
    -0.72
    à¨
    -0.71
    inder
    -0.71
    ager
    -0.70
    β
    -0.70
    ailed
    -0.69
    agers
    -0.69
    asers
    -0.68
    selling
    -0.68
    POSITIVE LOGITS
    ity
    0.87
    ilaterally
    0.75
     Slate
    0.70
    ession
    0.66
    ertodd
    0.66
     sanct
    0.65
     hiber
    0.65
    liness
    0.65
     quo
    0.63
    bard
    0.62
    Act Density 0.028%

    No Known Activations