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

    Neuronpedia

    INDEX
    Explanations

    adjectives relating to a certain type or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    descriptions that categorize or classify various subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LAN
    -0.71
    ULTS
    -0.67
    ERG
    -0.67
    BLE
    -0.67
    DS
    -0.67
    HAEL
    -0.66
    arks
    -0.65
    nut
    -0.65
     Dent
    -0.63
    MEN
    -0.63
    POSITIVE LOGITS
    entially
    0.81
    ãĤ¦ãĤ¹
    0.80
    ative
    0.74
    phabet
    0.74
    sort
    0.73
    auld
    0.71
    oscope
    0.70
     attm
    0.67
    hing
    0.66
    è
    0.65
    Act Density 0.017%

    No Known Activations