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

    Neuronpedia

    INDEX
    Explanations

    negative expressions of inability or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.85
     fhort
    -0.76
     houſe
    -0.75
     purpoſe
    -0.71
     ſtate
    -0.69
     poffe
    -0.69
     planas
    -0.66
     Efq
    -0.66
     Chriftian
    -0.66
    OGND
    -0.65
    POSITIVE LOGITS
     figure
    0.66
     find
    0.58
     disponibilités
    0.56
     VIAF
    0.55
    figure
    0.55
    find
    0.52
     FIND
    0.52
    Tahoma
    0.51
    مراجع
    0.48
    ArrowToggle
    0.47
    Act Density 0.140%

    No Known Activations