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

    Neuronpedia

    INDEX
    Explanations

    suggestions or requests for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McInt
    -0.15
    ierce
    -0.15
    erdale
    -0.14
    âl
    -0.14
     hen
    -0.14
    alone
    -0.14
    owell
    -0.14
    NOP
    -0.14
    MLE
    -0.14
    geh
    -0.14
    POSITIVE LOGITS
    Ãłng
    0.14
    uba
    0.14
    atta
    0.14
     voks
    0.13
    sett
    0.13
    ney
    0.13
    /lic
    0.13
    upiter
    0.13
    781
    0.13
    INA
    0.13
    Act Density 0.078%

    No Known Activations