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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing certainty and recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JAXB
    -0.63
     Baer
    -0.62
     antig
    -0.60
    malige
    -0.58
    Essentially
    -0.57
     NoSuch
    -0.56
     Essentially
    -0.56
    andescent
    -0.55
     članak
    -0.53
    xically
    -0.53
    POSITIVE LOGITS
     Definitely
    0.85
    Definitely
    0.83
     definitely
    0.81
     definately
    0.81
     Undoubtedly
    0.78
    ScopeManager
    0.77
    oubtedly
    0.76
    ConstraintMaker
    0.75
    writeFieldEnd
    0.71
     zeker
    0.70
    Act Density 0.265%

    No Known Activations