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

    Neuronpedia

    INDEX
    Explanations

    phrases in the format of "______ argues _____" with a focus on success and emotional wellbeing

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific symbol or character repeated throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oxide
    -0.71
     welf
    -0.70
     adulthood
    -0.65
     estranged
    -0.65
     dock
    -0.64
     charger
    -0.64
     antip
    -0.64
     accomp
    -0.63
    pped
    -0.62
     ignition
    -0.62
    POSITIVE LOGITS
    WHERE
    1.11
    yet
    1.05
    wait
    1.04
    there
    1.02
    they
    1.01
    why
    1.00
    BUT
    0.97
    among
    0.97
    until
    0.96
    sort
    0.95
    Act Density 0.046%

    No Known Activations