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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cromado
    -0.53
    发表于
    -0.53
    ceq
    -0.48
     solares
    -0.46
    seamnă
    -0.46
     réunions
    -0.46
    recated
    -0.46
     épaules
    -0.45
    だが
    -0.45
     furent
    -0.44
    POSITIVE LOGITS
    }{*}{}
    0.69
    <bos>
    0.66
     تضيفلها
    0.60
    zące
    0.58
    }>;
    0.58
    0.57
    äsentation
    0.57
    ⋱
    0.57
    enumii
    0.55
     tartalomajánló
    0.55
    Act Density 1.404%

    No Known Activations