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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of directions and locations

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to multiple perspectives or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquette
    -0.59
    ample
    -0.58
    oat
    -0.56
    ITION
    -0.55
     nevertheless
    -0.55
    hammad
    -0.54
    hound
    -0.54
    naire
    -0.53
    ĵĺ
    -0.53
    hemoth
    -0.53
    POSITIVE LOGITS
     standpoint
    1.42
     vantage
    1.38
     angles
    1.17
     sources
    1.11
     perspective
    1.11
     perspectives
    1.09
     afar
    0.92
     angle
    0.91
     backgrounds
    0.89
     onwards
    0.87
    Act Density 0.188%

    No Known Activations