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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts in texts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to monetary value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ern
    -0.80
     Ribbon
    -0.75
     Aval
    -0.72
     Puzz
    -0.72
     Edison
    -0.69
    Fra
    -0.65
     Plain
    -0.64
     Hilbert
    -0.64
     Nou
    -0.63
     Warfare
    -0.63
    POSITIVE LOGITS
    umes
    0.86
    ume
    0.85
    worth
    0.84
    iness
    0.78
    otation
    0.76
    imus
    0.75
    ensing
    0.75
    folios
    0.73
    ongs
    0.73
     worth
    0.72
    Act Density 0.020%

    No Known Activations