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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and international affairs

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political and economic issues, particularly concerning inclusivity and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortunately
    -0.55
     assures
    -0.55
     hopes
    -0.54
     fortunately
    -0.53
    hap
    -0.52
     marvel
    -0.52
    inguished
    -0.51
    !.
    -0.50
    ymes
    -0.48
    isms
    -0.48
    POSITIVE LOGITS
     solely
    0.81
     exclusively
    0.73
     purely
    0.72
     destro
    0.63
     excessively
    0.63
    only
    0.59
     overly
    0.58
     unilaterally
    0.58
     overtly
    0.58
     anything
    0.58
    Act Density 0.975%

    No Known Activations