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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or status

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words indicating progress or distance over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EntityItem
    -0.72
    olor
    -0.70
    chio
    -0.67
    vec
    -0.65
     Replacement
    -0.64
     Suc
    -0.64
     Spectrum
    -0.63
     Schultz
    -0.63
    nect
    -0.63
     Salad
    -0.63
    POSITIVE LOGITS
    ugu
    0.76
    ago
    0.70
    iasm
    0.65
    fetched
    0.64
     shy
    0.64
     gone
    0.63
     unsuccessful
    0.62
     unsuccessfully
    0.61
     suffice
    0.59
    ounding
    0.59
    Act Density 0.020%

    No Known Activations