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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or opinion about relational topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BibitemShut
    -0.96
     photolibrary
    -0.84
     doubtnut
    -0.80
     Könige
    -0.79
     myſelf
    -0.77
     Monfieur
    -0.76
     publick
    -0.75
    citenamefont
    -0.75
     Efq
    -0.75
     $_(
    -0.75
    POSITIVE LOGITS
    in
    0.65
    a
    0.63
    ’
    0.62
    so
    0.59
    we
    0.57
     }
    0.55
    i
    0.55
    '
    0.54
    </em>
    0.53
    this
    0.53
    Act Density 0.336%

    No Known Activations