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

    Neuronpedia

    INDEX
    Explanations

    various combinations of letters

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.78
    ct
    -0.71
    fal
    -0.62
    awatts
    -0.62
    roc
    -0.62
    hex
    -0.62
    iverpool
    -0.62
    cc
    -0.60
    bc
    -0.60
    ks
    -0.60
    POSITIVE LOGITS
    ERY
    1.26
    ICAL
    1.24
    ISH
    1.22
    IFIED
    1.22
    INS
    1.20
    ING
    1.19
    ERS
    1.19
    ITS
    1.19
    ITION
    1.19
    ICLE
    1.17
    Act Density 0.091%

    No Known Activations