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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -1.09
    ⓧ
    -0.88
     незавершена
    -0.87
    WireFormatLite
    -0.77
    PerformLayout
    -0.76
    AndEndTag
    -0.73
     betweenstory
    -0.70
    etheless
    -0.68
    нгредіє
    -0.67
    hyrchwyd
    -0.67
    POSITIVE LOGITS
    To
    1.28
     To
    1.20
    to
    0.91
    TO
    0.87
     TO
    0.79
    setTo
    0.56
    ToBe
    0.54
    tov
    0.54
    tq
    0.54
    为了
    0.53
    Act Density 0.214%

    No Known Activations