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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a shift or transition in a situation or context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Now" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [|
    -0.82
    acci
    -0.67
    VERTISEMENT
    -0.66
    icidal
    -0.63
    "},{"
    -0.60
    Interstitial
    -0.60
    chest
    -0.60
    aughed
    -0.59
    println
    -0.59
    cos
    -0.58
    POSITIVE LOGITS
    adays
    1.58
    here
    1.10
    heres
    0.78
     defunct
    0.78
    nir
    0.77
     NCT
    0.75
    IRT
    0.71
     embattled
    0.71
    terday
    0.70
     Deadline
    0.70
    Act Density 0.061%

    No Known Activations