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

    Neuronpedia

    INDEX
    Explanations

    words that indicate surprise or interest in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToProps
    -0.15
    ujet
    -0.15
    .toByteArray
    -0.15
    clud
    -0.14
    iniz
    -0.14
    athers
    -0.14
    /AFP
    -0.14
    èo
    -0.13
    thers
    -0.13
    either
    -0.13
    POSITIVE LOGITS
     crib
    0.16
    yo
    0.15
    hausen
    0.15
    ziel
    0.15
    gii
    0.15
    otto
    0.14
    ah
    0.14
    bie
    0.14
     ta
    0.14
    oose
    0.14
    Act Density 0.066%

    No Known Activations