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

    Neuronpedia

    INDEX
    Explanations

    expressions related to artistic achievements and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     annoying
    -0.64
     annoyance
    -0.61
    Basically
    -0.60
     IIRC
    -0.57
     Basically
    -0.57
     whatnot
    -0.56
    atisfactory
    -0.55
    sslich
    -0.54
     Presumably
    -0.54
    例文帳に追加
    -0.53
    POSITIVE LOGITS
     captured
    0.81
    __":
    0.78
     unfolding
    0.75
     reborn
    0.74
    __":
    0.71
     kasarigan
    0.71
     woven
    0.70
     interwoven
    0.70
     shaping
    0.67
     uniting
    0.67
    Act Density 0.357%

    No Known Activations