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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly those that begin with specific letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.70
    lvl
    -0.67
    warm
    -0.66
    uador
    -0.65
    etheless
    -0.62
    tics
    -0.60
    nesday
    -0.60
    adesh
    -0.58
     Thieves
    -0.58
    arl
    -0.58
    POSITIVE LOGITS
    ONSORED
    0.70
    itzer
    0.68
    utenberg
    0.64
     Dept
    0.62
    Department
    0.62
    ENSE
    0.59
    ourke
    0.59
    minster
    0.58
     bip
    0.58
    mann
    0.57
    Act Density 0.185%

    No Known Activations