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

    Neuronpedia

    INDEX
    Explanations

    words related to pathways or routes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of pathways or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kern
    -0.67
     bal
    -0.65
    rament
    -0.62
    ocratic
    -0.60
    ãģ®å®
    -0.59
     Kau
    -0.58
    grave
    -0.58
     Falk
    -0.57
    天
    -0.57
    avez
    -0.56
    POSITIVE LOGITS
    cape
    1.22
    ways
    1.14
    terday
    1.03
    uggest
    1.01
    mith
    0.98
    hip
    0.96
    hops
    0.94
    hips
    0.92
    afety
    0.88
    peed
    0.86
    Act Density 0.014%

    No Known Activations