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

    Neuronpedia

    INDEX
    Explanations

    words related to processes, functions, and actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owell
    -0.17
    274
    -0.17
    stal
    -0.17
    uos
    -0.16
    inese
    -0.15
    rawer
    -0.15
    ewood
    -0.15
     æ¥Ń
    -0.15
    .bunifuFlatButton
    -0.14
    лагод
    -0.14
    POSITIVE LOGITS
     contained
    0.25
     previous
    0.24
     proper
    0.22
     via
    0.21
     previously
    0.21
    contained
    0.20
     subsequent
    0.19
     spherical
    0.19
     exterior
    0.19
     correct
    0.18
    Act Density 0.068%

    No Known Activations