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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty and speculation in discussions about characters and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brio
    -0.78
    Herzliche
    -0.70
     variously
    -0.69
     diminution
    -0.68
     Надо
    -0.68
     guère
    -0.67
     salutary
    -0.67
     ―――――
    -0.67
     (;;)
    -0.66
    ^(@)
    -0.65
    POSITIVE LOGITS
     oftentimes
    0.70
    Personensuche
    0.60
     solidified
    0.59
     relatable
    0.58
    gnancy
    0.58
     stagnant
    0.57
    addGap
    0.57
     demnach
    0.57
     optique
    0.57
     StringField
    0.57
    Act Density 0.407%

    No Known Activations