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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or action

    oai_token-act-pair · gpt-3.5-turbo

    words related to visual characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IJ
    -0.77
    Wan
    -0.66
    CHA
    -0.65
     Toll
    -0.62
    Serv
    -0.59
     Q
    -0.58
    ENTION
    -0.58
    ij士
    -0.57
    Anything
    -0.55
    Submit
    -0.55
    POSITIVE LOGITS
    anchester
    0.83
    luster
    0.80
    warm
    0.77
    ipop
    0.71
    emon
    0.71
    igans
    0.70
    iberal
    0.68
    stro
    0.67
    ardless
    0.66
    udic
    0.66
    Act Density 0.060%

    No Known Activations