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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .prot
    -0.17
    åĻ
    -0.17
    ritte
    -0.17
    lya
    -0.16
    lor
    -0.16
    lion
    -0.15
    รม
    -0.15
    .lab
    -0.14
    à¸Ļà¸Ķ
    -0.14
    itte
    -0.14
    POSITIVE LOGITS
     adjud
    0.15
     Gy
    0.15
    ango
    0.15
    aised
    0.15
     ---------------------------------------------------------------------------↵
    0.14
    ules
    0.14
    udge
    0.14
     absorb
    0.14
    .Read
    0.13
    hal
    0.13
    Act Density 0.007%

    No Known Activations