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

    Neuronpedia

    INDEX
    Explanations

    themes of conflict and realism in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zan
    -0.94
    ģĸ
    -0.88
    ĵ
    -0.73
    untarily
    -0.67
    eem
    -0.66
    Ļ½
    -0.65
    ®
    -0.64
    ĩ
    -0.64
    gae
    -0.64
    §
    -0.63
    POSITIVE LOGITS
     which
    0.75
     whence
    0.74
     albeit
    0.68
     whereby
    0.65
     aka
    0.63
     however
    0.63
     namely
    0.62
    iest
    0.62
    Magikarp
    0.61
    liest
    0.61
    Act Density 0.200%

    No Known Activations