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

    Neuronpedia

    INDEX
    Explanations

    sentences containing commentary or opinions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" indicating existence or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.68
     notices
    -0.68
     Telesc
    -0.67
    itches
    -0.64
     encounters
    -0.63
     Commun
    -0.63
    eor
    -0.61
    know
    -0.61
    pox
    -0.61
     peg
    -0.60
    POSITIVE LOGITS
    rael
    1.12
    senal
    1.03
     definitely
    1.02
     hereby
    0.97
    nt
    0.96
     unlikely
    0.96
    olate
    0.96
    olation
    0.95
     likely
    0.94
    cussion
    0.92
    Act Density 0.587%

    No Known Activations