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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing the quality or ranking of something

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and phrases describing extreme qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenant
    -0.79
    fecture
    -0.77
    OPE
    -0.76
    visor
    -0.76
    ope
    -0.75
    matter
    -0.75
    ologue
    -0.74
    timer
    -0.74
    brance
    -0.74
    utan
    -0.74
    POSITIVE LOGITS
     aspects
    1.15
     inventions
    1.12
     fronts
    1.12
     facets
    1.11
     examples
    1.11
     occasions
    1.10
     avenues
    1.10
     instances
    1.09
     pillars
    1.09
     pieces
    1.07
    Act Density 0.139%

    No Known Activations