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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making a name for oneself or making a living

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal identity and reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nih
    -0.71
     directions
    -0.70
    hod
    -0.66
     completes
    -0.63
    ignt
    -0.60
     cran
    -0.60
    abc
    -0.59
     coupons
    -0.59
    apons
    -0.59
    author
    -0.58
    POSITIVE LOGITS
    ously
    0.83
    ouse
    0.78
    icz
    0.71
    uable
    0.70
    uch
    0.68
    amph
    0.67
    vre
    0.66
     Kingdoms
    0.66
    illo
    0.65
    lund
    0.63
    Act Density 0.077%

    No Known Activations