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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors and expressions of success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fatal
    -0.14
     Spare
    -0.14
    iform
    -0.13
    caffold
    -0.13
    986
    -0.13
    alar
    -0.13
     Inhal
    -0.13
     ÑģÑħод
    -0.13
     afar
    -0.13
    adena
    -0.13
    POSITIVE LOGITS
     testimony
    0.41
     proof
    0.40
     symbol
    0.39
     testament
    0.38
     indication
    0.38
     evidence
    0.38
     indicator
    0.35
     symbols
    0.35
     reminder
    0.34
     representation
    0.33
    Act Density 0.305%

    No Known Activations