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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and compliments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions of praise or positive evaluations.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     itſelf
    -0.83
     esternos
    -0.78
    RenderAtEndOf
    -0.74
     ourselves
    -0.73
     giustizia
    -0.71
     betweenstory
    -0.71
     himſelf
    -0.70
     noastre
    -0.70
     herself
    -0.67
    InjectAttribute
    -0.67
    POSITIVE LOGITS
     no
    0.68
     No
    0.63
    RequiresApi
    0.62
    ar
    0.59
     big
    0.58
     Good
    0.58
     pe
    0.58
     A
    0.58
     
    0.57
     a
    0.57
    Act Density 0.220%

    No Known Activations