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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of beginnings or starting something new

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to upcoming events or new releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.78
    Äĩ
    -0.74
    emort
    -0.73
    ère
    -0.72
    hent
    -0.70
    thood
    -0.68
    mentation
    -0.68
    encer
    -0.68
    ucci
    -0.68
    £ı
    -0.67
    POSITIVE LOGITS
    ISSION
    0.83
     stairs
    0.69
     seams
    0.69
     pasture
    0.67
     adolesc
    0.66
     toile
    0.66
     grabs
    0.65
     maze
    0.64
     volunt
    0.64
     baseline
    0.64
    Act Density 0.363%

    No Known Activations