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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to conspiracy theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ophon
    -0.78
    artney
    -0.77
    nea
    -0.77
    pex
    -0.74
    emale
    -0.72
    manuel
    -0.71
    oves
    -0.69
    onga
    -0.68
    iens
    -0.66
    cially
    -0.66
    POSITIVE LOGITS
     rumours
    0.97
     rumors
    0.97
     rumor
    0.94
     speculate
    0.83
     Rum
    0.81
     concerning
    0.81
     regarding
    0.80
     theories
    0.78
     inacc
    0.74
     errone
    0.73
    Act Density 0.097%

    No Known Activations