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

    Neuronpedia

    INDEX
    Explanations

    significant verbs or actions related to experiences and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    151
    -0.16
    imore
    -0.15
    ibal
    -0.15
    elligence
    -0.15
     kinh
    -0.14
    getline
    -0.14
    ibir
    -0.14
    lÃŃÄį
    -0.14
    isay
    -0.14
    illon
    -0.13
    POSITIVE LOGITS
    allee
    0.14
     envelopes
    0.14
    PFN
    0.14
    _HERSHEY
    0.14
    alt
    0.14
    612
    0.14
     envelope
    0.14
    ets
    0.14
    ode
    0.14
    .libs
    0.14
    Act Density 0.039%

    No Known Activations