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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or refutation of ideas or claims

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to debunking myths or unsupported claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.85
     actionGroup
    -0.73
     unfocusedRange
    -0.67
    itaire
    -0.67
    rha
    -0.66
    ophon
    -0.66
    icult
    -0.65
    oided
    -0.65
    ishable
    -0.64
     Suc
    -0.64
    POSITIVE LOGITS
     assertions
    1.62
     claims
    1.56
     claim
    1.48
     assertion
    1.47
     hypotheses
    1.42
     accusations
    1.37
     notion
    1.35
     allegation
    1.35
     assumptions
    1.35
     allegations
    1.33
    Act Density 0.573%

    No Known Activations