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

    Neuronpedia

    INDEX
    Explanations

    conditional expressions indicating suggestions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cratch
    -0.17
    ách
    -0.16
    otros
    -0.15
    zap
    -0.15
    orque
    -0.15
    eteor
    -0.15
    PÅĻi
    -0.15
    å®
    -0.14
    oog
    -0.14
    elize
    -0.14
    POSITIVE LOGITS
    _SMALL
    0.16
    ://"
    0.15
     note
    0.15
    ecta
    0.15
    wend
    0.14
    roi
    0.14
    HT
    0.14
     useful
    0.14
    gram
    0.13
    .communication
    0.13
    Act Density 0.030%

    No Known Activations