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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "surprise" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.62
     fær
    -0.59
    IMDG
    -0.56
    schirm
    -0.55
    vka
    -0.55
    ArgsConstructor
    -0.54
    >{@
    -0.54
     sécur
    -0.54
    maxn
    -0.53
    glBind
    -0.53
    POSITIVE LOGITS
     surprise
    3.12
     Surprise
    2.83
    surprise
    2.66
     surprised
    2.64
     surprises
    2.57
    Surprise
    2.53
     surprising
    2.25
     surpris
    2.25
    surprised
    2.24
     sorpresa
    2.05
    Act Density 0.044%

    No Known Activations