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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and contrasts in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Įĵ
    -0.16
     EITHER
    -0.15
    ÑĨо
    -0.14
     neither
    -0.14
    UIApplication
    -0.14
    Mixin
    -0.14
    ÙĦÛĮÙĩ
    -0.14
    .yy
    -0.14
    Ĥ
    -0.13
    SURE
    -0.13
    POSITIVE LOGITS
     downright
    0.46
     outright
    0.42
     border
    0.29
     actively
    0.25
     borders
    0.24
     actual
    0.22
     Border
    0.22
    border
    0.22
     actually
    0.21
     flat
    0.21
    Act Density 0.141%

    No Known Activations