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

    Neuronpedia

    INDEX
    Explanations

    words that convey negativity or dismissal towards concepts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trib
    -0.14
    upa
    -0.14
     ëĦ¤ìĿ´íĬ¸
    -0.14
    /apt
    -0.14
    ilty
    -0.13
    ĮĢ
    -0.13
    ylko
    -0.13
    appa
    -0.13
    resden
    -0.13
    .tpl
    -0.13
    POSITIVE LOGITS
     unless
    0.19
    unless
    0.18
    .LookAndFeel
    0.16
     altogether
    0.16
    avigation
    0.15
    æİī
    0.15
     because
    0.15
    ROL
    0.15
    enever
    0.14
    ALS
    0.14
    Act Density 0.132%

    No Known Activations