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

    Neuronpedia

    INDEX
    Explanations

    words related to a person's name followed by a number, possibly indicating a version or iteration

    oai_token-act-pair · gpt-3.5-turbo

    words containing the substring "oll"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOD
    -0.73
    hered
    -0.68
     Flavoring
    -0.66
    ©¶æ
    -0.66
    ITAL
    -0.63
    âĸ¬âĸ¬
    -0.63
    PDATE
    -0.60
    RET
    -0.59
    çĶ°
    -0.59
    quickShipAvailable
    -0.57
    POSITIVE LOGITS
    ipop
    1.31
    usk
    1.10
    iard
    1.03
    ocks
    1.02
    iday
    0.96
    iffe
    0.95
    inger
    0.93
    ars
    0.93
    abor
    0.89
    aday
    0.89
    Act Density 0.023%

    No Known Activations