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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visibility and observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.86
     tartalomajánló
    -0.79
    #+#
    -0.75
    /*
    -0.73
     intptr
    -0.73
     autorytatywna
    -0.64
    曖昧さ回避
    -0.63
    kania
    -0.61
    RegressionTest
    -0.61
    :✨
    -0.61
    POSITIVE LOGITS
    idać
    0.83
     widać
    0.72
     visible
    0.69
     видно
    0.67
    lihatan
    0.63
     visibles
    0.62
     näky
    0.61
     hear
    0.61
     jelas
    0.59
    看得
    0.58
    Act Density 0.192%

    No Known Activations