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

    Neuronpedia

    INDEX
    Explanations

    words related to organization and processing

    oai_token-act-pair · gpt-3.5-turbo

    past tense action verbs related to processing and organizing items or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sutherland
    -0.60
     secretaries
    -0.58
     Glover
    -0.56
    esa
    -0.55
     compulsion
    -0.54
     uncanny
    -0.54
    mber
    -0.54
     purse
    -0.54
    ¥µ
    -0.53
     Sack
    -0.53
    POSITIVE LOGITS
     properly
    1.08
     correctly
    1.07
     anew
    0.97
     into
    0.93
     manually
    0.89
     separately
    0.89
     externally
    0.86
     INTO
    0.86
     successfully
    0.86
     safely
    0.85
    Act Density 0.261%

    No Known Activations