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

    Neuronpedia

    INDEX
    Explanations

    instances where something is almost reaching a certain state or outcome

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.67
    AIN
    -0.67
    ãĤ¸
    -0.65
    NZ
    -0.65
    天
    -0.63
    Sov
    -0.63
    udeb
    -0.63
    OOL
    -0.62
    rain
    -0.62
    UL
    -0.62
    POSITIVE LOGITS
    sighted
    1.02
     minded
    0.90
     thereto
    0.88
    paren
    0.85
     proximity
    0.81
     enough
    0.78
     resemblance
    0.73
    rentices
    0.73
    iths
    0.73
    minded
    0.71
    Act Density 0.025%

    No Known Activations