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

    Neuronpedia

    INDEX
    Explanations

    words related to unity and coming together

    oai_token-act-pair · gpt-3.5-turbo

    concepts of unity and togetherness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.82
    erenn
    -0.77
    aches
    -0.71
     Advertisement
    -0.70
    =-=-=-=-=-=-=-=-
    -0.69
    den
    -0.68
    á
    -0.67
    NULL
    -0.64
    advant
    -0.64
    dark
    -0.63
    POSITIVE LOGITS
     united
    0.88
     unite
    0.79
    essional
    0.78
    icut
    0.74
    éĹĺ
    0.74
    arity
    0.73
    mble
    0.72
     unified
    0.71
     unity
    0.71
    ification
    0.70
    Act Density 0.011%

    No Known Activations