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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Generally"

    oai_token-act-pair · gpt-3.5-turbo

    phrases or contexts that convey a generalization or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.74
    lyn
    -0.74
     Kyl
    -0.71
    gur
    -0.71
    ilion
    -0.70
    lez
    -0.70
     Seat
    -0.69
     Orchestra
    -0.69
     Frenzy
    -0.68
     Odyssey
    -0.68
    POSITIVE LOGITS
     regarded
    1.04
     speaking
    0.98
     frowned
    0.90
     categorized
    0.87
     accepted
    0.83
     disliked
    0.82
     preferring
    0.79
     appreciated
    0.79
     considered
    0.78
     disclaim
    0.76
    Act Density 0.014%

    No Known Activations