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

    Neuronpedia

    INDEX
    Explanations

    keywords related to highlighting specific items or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.96
    yss
    -0.81
    perty
    -0.71
     confir
    -0.70
    anwhile
    -0.67
     godd
    -0.67
     adolesc
    -0.66
    idth
    -0.65
    wake
    -0.64
    RR
    -0.64
    POSITIVE LOGITS
    lights
    1.47
    ter
    1.07
    ting
    1.00
    ty
    0.94
    light
    0.93
    eele
    0.91
    ters
    0.91
    tery
    0.90
    lighting
    0.88
    kick
    0.86
    Act Density 0.026%

    No Known Activations