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

    Neuronpedia

    INDEX
    Explanations

    references to factual information in a text

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "facts" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.92
    ovo
    -0.84
    osi
    -0.82
    isoft
    -0.80
    antha
    -0.79
    zik
    -0.78
    rint
    -0.77
    ateurs
    -0.76
    irl
    -0.76
    hod
    -0.76
    POSITIVE LOGITS
    facts
    0.94
     facts
    0.93
    heet
    0.87
    fulness
    0.83
     inacc
    0.82
    fact
    0.82
    telling
    0.78
     unfold
    0.72
     pertaining
    0.71
     relating
    0.69
    Act Density 0.022%

    No Known Activations