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

    Neuronpedia

    INDEX
    Explanations

    references to situations involving decision-making or choices

    oai_token-act-pair · gpt-3.5-turbo

    the word "dec" along with its variations, likely indicating references to decisions or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.87
    Reviewer
    -0.84
    ansas
    -0.78
     Dragonbound
    -0.74
    ĪĴ
    -0.73
    WAYS
    -0.72
    ħĭ
    -0.68
    folios
    -0.68
     Graveyard
    -0.67
    allery
    -0.67
    POSITIVE LOGITS
    rypted
    1.40
    oded
    1.31
    ryption
    1.29
    ibel
    1.23
    oder
    1.10
    isions
    1.10
    ried
    1.06
    ribed
    1.03
    imet
    1.02
    ently
    1.02
    Act Density 0.012%

    No Known Activations