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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antaranya
    -0.65
     daß
    -0.60
    specially
    -0.60
     antaranya
    -0.59
     that
    -0.57
    WriteTagHelper
    -0.53
     bahawa
    -0.53
     thats
    -0.53
     MEANS
    -0.52
     it
    -0.52
    POSITIVE LOGITS
     something
    0.96
    something
    0.80
     Something
    0.76
    Something
    0.75
     effectively
    0.68
     further
    0.66
    ThroughAttribute
    0.64
    VersionUID
    0.64
     något
    0.63
    hyrchwyd
    0.63
    Act Density 0.571%

    No Known Activations