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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of condemnation or denouncement of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.81
    IER
    -0.70
     membr
    -0.68
     Wonders
    -0.68
    emis
    -0.66
    BLIC
    -0.65
    seed
    -0.63
    icle
    -0.63
    NetMessage
    -0.62
    aldo
    -0.62
    POSITIVE LOGITS
     condemn
    0.90
     homophobic
    0.83
     unequivocally
    0.82
    ations
    0.79
     atrocities
    0.79
     condemning
    0.79
     harshly
    0.75
     condemnation
    0.75
    ifiable
    0.75
    urous
    0.75
    Act Density 0.055%

    No Known Activations