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

    Neuronpedia

    INDEX
    Explanations

    global or overall evaluations and judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote an overall evaluation or summary assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caf
    -0.75
     Bry
    -0.71
     Debor
    -0.68
    ©¶æ
    -0.66
    lez
    -0.64
     Frie
    -0.64
    ÅŁ
    -0.64
     Claud
    -0.64
     Minute
    -0.63
    cells
    -0.63
    POSITIVE LOGITS
     usefulness
    0.88
     momentum
    0.84
     attractiveness
    0.84
     stability
    0.83
     effectiveness
    0.82
     improvement
    0.81
     length
    0.80
     impression
    0.75
     strategy
    0.75
    iance
    0.75
    Act Density 0.039%

    No Known Activations