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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating great extent or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate exceeding limits or going too far in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urated
    -0.64
    leased
    -0.63
    ipation
    -0.60
     LOT
    -0.60
    bed
    -0.58
     Nep
    -0.58
    urse
    -0.57
    leases
    -0.57
    ellation
    -0.55
    rats
    -0.55
    POSITIVE LOGITS
     overboard
    0.89
    WARD
    0.79
     lengths
    0.75
     towards
    0.73
     toward
    0.72
    irtual
    0.72
    reaching
    0.72
     beyond
    0.70
     backwards
    0.69
     ast
    0.68
    Act Density 0.056%

    No Known Activations