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

    Neuronpedia

    INDEX
    Explanations

    mentions of education

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically the presence of commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Animal
    -0.83
     Languages
    -0.71
     Animals
    -0.69
    sembly
    -0.67
    EY
    -0.66
    eat
    -0.66
    ARE
    -0.66
     Breed
    -0.65
     tagging
    -0.65
     Role
    -0.65
    POSITIVE LOGITS
     recognised
    0.77
     sympt
    0.73
    aran
    0.69
     braces
    0.68
     bras
    0.67
     felt
    0.66
     detected
    0.65
     hijacked
    0.63
     detectable
    0.62
     convertible
    0.62
    Act Density 0.000%

    No Known Activations