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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and their actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to political criticism and controversies involving specific politicians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.82
     prest
    -0.67
     Cf
    -0.64
     ---------
    -0.63
    pires
    -0.58
     ~/
    -0.58
    PDATED
    -0.57
    =~
    -0.56
     dots
    -0.56
     Somewhere
    -0.56
    POSITIVE LOGITS
     harshly
    0.94
     accusing
    0.88
     merciless
    0.84
     hypocrisy
    0.84
     for
    0.81
     hypoc
    0.80
     relentlessly
    0.80
     alleging
    0.79
     repeatedly
    0.76
     tactics
    0.76
    Act Density 0.390%

    No Known Activations