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

    Neuronpedia

    INDEX
    Explanations

    mentions of closures or shutdowns

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration or conditions related to "for" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clair
    -0.70
     Caption
    -0.68
    ouf
    -0.66
    ilant
    -0.61
     approached
    -0.61
    mare
    -0.61
    jad
    -0.61
     awoken
    -0.60
     flyer
    -0.60
    æѦ
    -0.59
    POSITIVE LOGITS
     reasons
    1.37
     purposes
    1.36
     sake
    1.15
    geries
    1.05
     awhile
    1.03
    bidden
    1.00
    gotten
    0.94
     fear
    0.93
     instance
    0.88
    cible
    0.88
    Act Density 0.215%

    No Known Activations