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

    Neuronpedia

    INDEX
    Explanations

    terms related to intentional actions and explicit definitions or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.72
    tagHelperRunner
    -0.72
     illiteracy
    -0.64
    principalColumn
    -0.61
     Jefus
    -0.61
     scaler
    -0.59
     pascal
    -0.59
     Majefty
    -0.58
     Highlands
    -0.58
     undeveloped
    -0.57
    POSITIVE LOGITS
     intentional
    0.87
     intentionally
    0.80
     deliberately
    0.73
    刻意
    0.70
     deliberate
    0.69
    intention
    0.67
     consciously
    0.66
     sengaja
    0.65
     purposely
    0.64
    desired
    0.63
    Act Density 0.740%

    No Known Activations