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

    Neuronpedia

    INDEX
    Explanations

    references to condemnation and criticism of violent or discriminatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arguments
    -0.19
     Arguments
    -0.19
     arguing
    -0.17
     controversial
    -0.16
    reve
    -0.15
    Arguments
    -0.15
     contentious
    -0.15
     Argument
    -0.15
     complaining
    -0.15
    arguments
    -0.14
    POSITIVE LOGITS
     condemn
    0.37
     condemnation
    0.35
    -cond
    0.35
     condemned
    0.33
     condem
    0.33
    cond
    0.32
     condemning
    0.30
     cond
    0.30
     solidarity
    0.28
     Cond
    0.28
    Act Density 0.118%

    No Known Activations