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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that denote existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocracy
    -0.75
     unfocusedRange
    -0.72
    iew
    -0.67
    ographer
    -0.66
    ocaust
    -0.65
    gow
    -0.64
    inav
    -0.63
    afety
    -0.63
    ioch
    -0.62
    teness
    -0.62
    POSITIVE LOGITS
     respectively
    1.43
     trademarks
    1.22
     mutually
    1.12
     alike
    1.11
     examples
    1.08
     jointly
    1.03
     staples
    1.00
     both
    1.00
     fronts
    0.99
     pillars
    0.98
    Act Density 0.233%

    No Known Activations