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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions that have a negative impact or intent

    oai_token-act-pair · gpt-3.5-turbo

    activites or phrases suggesting subversion or damage to credibility or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    area
    -0.65
    cise
    -0.64
    onna
    -0.63
    ëĭ
    -0.63
    sa
    -0.61
    lov
    -0.61
    Flo
    -0.61
    ather
    -0.60
    enne
    -0.59
    ann
    -0.59
    POSITIVE LOGITS
     havoc
    0.89
     undermin
    0.81
    lessly
    0.70
    xual
    0.70
     undermining
    0.68
    amental
    0.67
    ments
    0.66
     livelihood
    0.66
     morale
    0.64
     Mn
    0.64
    Act Density 0.044%

    No Known Activations