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

    Neuronpedia

    INDEX
    Explanations

    terms related to non-discrimination and equal opportunity policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.20
    eward
    -0.19
    azon
    -0.16
    ternet
    -0.15
    iction
    -0.15
    icus
    -0.15
    amodel
    -0.14
    ichten
    -0.14
    ullo
    -0.14
    orgh
    -0.14
    POSITIVE LOGITS
     Lage
    0.15
     simplex
    0.14
    áo
    0.14
    aldi
    0.14
    nga
    0.14
    aniu
    0.14
     looph
    0.13
     sint
    0.13
    hes
    0.13
    nda
    0.13
    Act Density 0.031%

    No Known Activations