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

    Neuronpedia

    INDEX
    Explanations

    words related to political and social ideologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various political ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tesy
    -0.78
    ecause
    -0.74
    accompanied
    -0.71
    shown
    -0.67
     speedy
    -0.67
    FACE
    -0.65
    ilings
    -0.64
    ruciating
    -0.63
    upon
    -0.63
    perty
    -0.63
    POSITIVE LOGITS
    geist
    0.89
    rist
    0.88
    ist
    0.87
    ess
    0.83
    oad
    0.81
    opol
    0.80
    ists
    0.79
    essed
    0.77
     tendencies
    0.76
    otle
    0.76
    Act Density 0.028%

    No Known Activations