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

    Neuronpedia

    INDEX
    Explanations

    various characters used in formatting or structure within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclud
    -0.67
     explan
    -0.66
     agre
    -0.65
     elig
    -0.65
     assum
    -0.64
     accordingly
    -0.60
     earlier
    -0.60
     dilig
    -0.58
     accomp
    -0.58
     arrog
    -0.57
    POSITIVE LOGITS
    pmwiki
    1.17
    Flickr
    1.16
    photos
    1.11
    Getty
    1.01
    ËĪ
    0.97
    wire
    0.97
    src
    0.95
    images
    0.94
    AFP
    0.93
    archives
    0.93
    Act Density 0.031%

    No Known Activations