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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate something is logical or reasonable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vÄĽdom
    -0.20
    rega
    -0.16
    ůr
    -0.16
    959
    -0.15
    asca
    -0.15
    emens
    -0.15
    á»±
    -0.15
    IENT
    -0.15
    ss
    -0.14
    enis
    -0.14
    POSITIVE LOGITS
    ersh
    0.14
    uyá»ĩt
    0.14
    ryption
    0.14
    ://%
    0.14
    коÑĤ
    0.14
     invested
    0.14
    842
    0.13
    fern
    0.13
    initializer
    0.13
    Č
    0.13
    Act Density 0.015%

    No Known Activations