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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social justice and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.07
     myſelf
    -0.95
    setVerticalGroup
    -0.91
    invokeLater
    -0.87
    ValueStyle
    -0.84
     raiſ
    -0.83
     Efq
    -0.82
     ་་
    -0.82
     itſelf
    -0.82
     CreateTagHelper
    -0.81
    POSITIVE LOGITS
    .
    1.60
    !
    1.59
    ;
    1.54
    ?
    1.28
    .
    1.25
    。
    1.17
    .}
    1.14
    ;
    1.09
    .\\
    1.08
    ."
    1.07
    Act Density 1.150%

    No Known Activations