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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating connections or contrasts in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Salam
    -0.39
     {}));
    -0.36
     Vert
    -0.36
     Cem
    -0.36
     certain
    -0.36
    tempat
    -0.36
    [...]
    -0.35
     Common
    -0.35
     Stomp
    -0.34
     wurden
    -0.34
    POSITIVE LOGITS
     Grüsse
    0.68
    rungsseite
    0.66
    InputTagHelper
    0.64
    出版年
    0.63
    iconque
    0.62
     Italij
    0.60
     poffe
    0.60
     himſelf
    0.60
     saveiro
    0.59
    -------------</
    0.59
    Act Density 0.748%

    No Known Activations