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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.65
    BAT
    -0.65
    tsky
    -0.64
    Js
    -0.63
    ARC
    -0.63
     Barr
    -0.58
    chy
    -0.58
    lyak
    -0.58
    azar
    -0.57
     Bris
    -0.56
    POSITIVE LOGITS
     ever
    1.46
     anything
    1.20
     EVER
    1.17
    anything
    1.10
     any
    1.07
     anybody
    1.05
     anyone
    1.03
     slightest
    1.02
     anywhere
    0.98
     ANY
    0.93
    Act Density 0.092%

    No Known Activations