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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating cooperation, collaboration, or unity among multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating collaboration or coming together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erved
    -0.65
    Secondly
    -0.64
    lean
    -0.63
    etch
    -0.63
     Blasio
    -0.63
    lesi
    -0.63
    vik
    -0.62
    arted
    -0.62
    clud
    -0.61
     Reincarn
    -0.61
    POSITIVE LOGITS
     unified
    0.88
     common
    0.87
     cohesive
    0.84
     mutually
    0.84
     mutual
    0.82
     synerg
    0.82
     form
    0.81
     unity
    0.78
     harmony
    0.74
     forming
    0.74
    Act Density 0.482%

    No Known Activations