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

    Neuronpedia

    INDEX
    Explanations

    references to attendance or participation in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pouvoit
    -0.79
     feroit
    -0.76
     desmotivaciones
    -0.75
     plufieurs
    -0.75
     avoient
    -0.73
     auroit
    -0.69
     zijne
    -0.68
     ainfi
    -0.67
     increí
    -0.65
     étoient
    -0.65
    POSITIVE LOGITS
     Extra
    0.67
     Among
    0.66
    Extra
    0.64
     EXTRA
    0.62
    extra
    0.62
     При
    0.62
     luck
    0.61
     attendance
    0.60
     Ideal
    0.58
    mc
    0.57
    Act Density 0.423%

    No Known Activations