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

    Neuronpedia

    INDEX
    Explanations

    declarative statements with the word "know" followed by some information or assertion

    oai_token-act-pair · gpt-3.5-turbo

    recurrent phrases asserting knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.81
    onding
    -0.80
    isco
    -0.70
    orthy
    -0.69
    phrine
    -0.69
    ermanent
    -0.68
     sidx
    -0.67
     pione
    -0.66
    achus
    -0.65
    aukee
    -0.63
    POSITIVE LOGITS
     firsthand
    1.20
     plenty
    1.02
     how
    1.00
     why
    0.96
     anecd
    0.93
     what
    0.91
     exactly
    0.91
     nothing
    0.90
     lots
    0.89
     many
    0.85
    Act Density 0.040%

    No Known Activations