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

    Neuronpedia

    INDEX
    Explanations

    negations related to the concept of existence or reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     piú
    -0.61
    pondre
    -0.57
     wijze
    -0.54
     ElementRef
    -0.53
     zijne
    -0.53
     början
    -0.52
     alcuna
    -0.52
     nessuna
    -0.50
     staden
    -0.50
     použití
    -0.50
    POSITIVE LOGITS
    <bos>
    0.91
    t
    0.73
    IfNot
    0.65
    んじゃない
    0.53
    rett
    0.53
     ratt
    0.52
     Aussie
    0.52
    tim
    0.52
    tsch
    0.52
     Arty
    0.51
    Act Density 0.097%

    No Known Activations