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

    Neuronpedia

    INDEX
    Explanations

    words related to unity or being together

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "united" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.84
    erenn
    -0.76
    aches
    -0.72
    =-=-=-=-=-=-=-=-
    -0.70
    phrine
    -0.69
    acher
    -0.69
    den
    -0.66
     Advertisement
    -0.65
    Ö¼
    -0.64
     Revelations
    -0.64
    POSITIVE LOGITS
    essional
    0.77
     united
    0.75
    arity
    0.75
    ification
    0.75
     unity
    0.73
    éĹĺ
    0.72
    hall
    0.71
    Leader
    0.71
    itarian
    0.69
     unite
    0.69
    Act Density 0.027%

    No Known Activations