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

    Neuronpedia

    INDEX
    Explanations

    punctuations and numerals that signal separate thoughts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.99
    ngdoc
    -0.97
    ValueStyle
    -0.82
    awaiter
    -0.73
    -0.71
    Descripció
    -0.69
    sizeCache
    -0.68
    Erreferentziak
    -0.67
    ⁩
    -0.65
    EReference
    -0.65
    POSITIVE LOGITS
     hope
    1.02
    Hope
    1.01
     Hope
    0.99
    Hopefully
    0.96
     Hopefully
    0.91
     hopefully
    0.86
     Espero
    0.84
    Наде
    0.84
     espero
    0.83
    いかが
    0.82
    Act Density 0.113%

    No Known Activations