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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer operations and file management

    oai_token-act-pair · gpt-3.5-turbo

    technical terms associated with software functionality and scanning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enture
    -0.76
    jah
    -0.74
    ppe
    -0.72
    ulture
    -0.69
    fal
    -0.66
    reau
    -0.65
    gal
    -0.64
    akening
    -0.64
    rolet
    -0.64
    rez
    -0.63
    POSITIVE LOGITS
     automatically
    1.26
     dynamically
    0.96
     incoming
    0.91
     notifications
    0.84
     randomly
    0.83
     itself
    0.82
     detects
    0.81
     EVERY
    0.75
     milliseconds
    0.74
     random
    0.73
    Act Density 0.441%

    No Known Activations