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

    Neuronpedia

    INDEX
    Explanations

    negations and verbs associated with limitations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lobby
    -0.18
     Leopard
    -0.17
    .writeInt
    -0.17
     Lear
    -0.17
     Lac
    -0.17
    laz
    -0.16
     Lambert
    -0.16
    etto
    -0.16
    chner
    -0.16
     Lifestyle
    -0.16
    POSITIVE LOGITS
     long
    0.70
    long
    0.61
    -long
    0.56
    éķ¿
    0.54
     Long
    0.54
    _long
    0.53
    .long
    0.52
    Long
    0.52
     LONG
    0.52
    éķ·
    0.47
    Act Density 0.219%

    No Known Activations