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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or changes being done to something

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Shift
    -0.78
    Operation
    -0.70
    shift
    -0.66
    robe
    -0.65
    knife
    -0.63
     actionGroup
    -0.61
     bush
    -0.60
     unlaw
    -0.60
    yip
    -0.59
    pole
    -0.58
    POSITIVE LOGITS
    ometimes
    0.82
    ĸļ
    0.76
    ependent
    0.73
    omorphic
    0.72
    entious
    0.72
    Apr
    0.72
    inently
    0.71
    ãĤ´
    0.71
    £ı
    0.69
     by
    0.69
    Act Density 0.291%

    No Known Activations