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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a predominant trend or characteristic within a larger group

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of the word "mostly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anth
    -0.82
    Reviewer
    -0.75
     Kard
    -0.74
    retched
    -0.68
    ITH
    -0.68
    iry
    -0.67
    ylan
    -0.67
    pload
    -0.66
    asel
    -0.66
    retch
    -0.65
    POSITIVE LOGITS
     consist
    0.86
     consisted
    0.81
     comprised
    0.75
     consists
    0.74
    tenance
    0.74
     consisting
    0.73
     disappoint
    0.71
     populated
    0.70
     foc
    0.69
     cloudy
    0.68
    Act Density 0.021%

    No Known Activations