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

    Neuronpedia

    INDEX
    Explanations

    phrases related to shifts in attitudes and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -1.23
    ;
    -0.83
    ?
    -0.82
    !
    -0.82
    ,
    -0.77
    .,
    -0.67
    :
    -0.65
    ).
    -0.65
    ."
    -0.65
    )
    -0.64
    POSITIVE LOGITS
    AddTagHelper
    1.10
     Efq
    1.07
    CppMethod
    1.03
     ModelExpression
    1.02
    клопе
    0.96
     مرئيه
    0.96
    GEBURTS
    0.89
    NUMX
    0.88
     CreateTagHelper
    0.86
    setVerticalGroup
    0.86
    Act Density 1.117%

    No Known Activations