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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating suitability or appropriateness for specific items or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    : 
    -0.56
    expandindo
    -0.53
     Herod
    -0.52
     gums
    -0.51
     mediodía
    -0.51
     devrez
    -0.49
     virginity
    -0.48
     TestBed
    -0.48
     Jehová
    -0.48
     invern
    -0.48
    POSITIVE LOGITS
     forState
    0.73
    exitRule
    0.62
     handling
    0.62
     holding
    0.61
    écial
    0.61
    для
    0.60
    wendung
    0.59
    FontOfSize
    0.59
     Anf
    0.59
    mitos
    0.59
    Act Density 0.360%

    No Known Activations