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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     say
    -1.00
     says
    -0.89
     saying
    -0.86
     said
    -0.84
    say
    -0.83
     Says
    -0.82
     SAY
    -0.81
    saying
    -0.81
    Says
    -0.79
    says
    -0.75
    POSITIVE LOGITS
     regretted
    0.67
     hoped
    0.63
     liever
    0.61
     expected
    0.58
    DrawerToggle
    0.56
    ImageContext
    0.56
    oredCriteria
    0.54
     believed
    0.54
     doubted
    0.54
     regrets
    0.53
    Act Density 0.254%

    No Known Activations