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

    Neuronpedia

    INDEX
    Explanations

    terms associated with capabilities and possibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nia
    -0.17
    nger
    -0.16
     RootState
    -0.15
    oe
    -0.14
    çŃ
    -0.14
    cer
    -0.14
     convo
    -0.14
    iams
    -0.13
    an
    -0.13
    nder
    -0.13
    POSITIVE LOGITS
    /stdc
    0.16
    prung
    0.14
    ingle
    0.14
    erval
    0.14
    bstract
    0.14
    ascar
    0.14
    DirectoryName
    0.14
     Sa
    0.13
    zman
    0.13
    ëĿ½
    0.13
    Act Density 0.350%

    No Known Activations