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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant issues or notable characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.85
    AutoScaleMode
    -0.76
    يميديا
    -0.69
    expandindo
    -0.69
     piele
    -0.68
     Administrativna
    -0.67
     Shakspeare
    -0.65
     Shaksp
    -0.63
     Roskov
    -0.62
     downvotes
    -0.61
    POSITIVE LOGITS
     question
    0.58
    那就是
    0.56
    :
    0.54
     namely
    0.53
    namely
    0.52
    ——
    0.51
     called
    0.51
    —
    0.51
     I
    0.51
    withIdentifier
    0.49
    Act Density 0.521%

    No Known Activations