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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "think" followed by a numerical value indicating certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    expressions of doubt or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.98
     pione
    -0.81
    pez
    -0.78
    Vers
    -0.69
    oxide
    -0.67
    alm
    -0.67
     earthqu
    -0.67
     subur
    -0.67
    redients
    -0.66
    origin
    -0.66
    POSITIVE LOGITS
     anybody
    1.56
     anyone
    1.55
     anything
    1.24
     any
    1.22
     anymore
    1.14
     nor
    1.09
     ANY
    1.05
     anywhere
    1.01
     ever
    0.95
     whatsoever
    0.92
    Act Density 0.114%

    No Known Activations