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

    Neuronpedia

    INDEX
    Explanations

    words related to additional information or actions beyond the main context

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jam
    -0.72
    agus
    -0.70
    acious
    -0.69
    heat
    -0.68
    ash
    -0.67
    ASE
    -0.67
    enter
    -0.66
     Chaser
    -0.65
    Earth
    -0.61
     Bout
    -0.60
    POSITIVE LOGITS
     includ
    0.89
     includes
    0.82
     cautioned
    0.80
     anecd
    0.79
     noteworthy
    0.78
     occasionally
    0.75
     included
    0.74
     congratulated
    0.74
     optionally
    0.73
     contributed
    0.72
    Act Density 0.094%

    No Known Activations