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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dissatisfaction or disappointment in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.72
     ModelExpression
    -0.68
    setVerticalGroup
    -0.63
     relâche
    -0.63
    tagHelperRunner
    -0.61
    ftagPool
    -0.61
    }],
    -0.60
    AndEndTag
    -0.59
     تضيفلها
    -0.59
    principalTable
    -0.59
    POSITIVE LOGITS
     anonymous
    0.64
     attendee
    0.63
     dissatisfied
    0.59
     parishi
    0.59
     participant
    0.58
     insured
    0.58
     villager
    0.57
     unemployed
    0.56
     disgusted
    0.56
     worshi
    0.56
    Act Density 0.206%

    No Known Activations