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

    Neuronpedia

    INDEX
    Explanations

    mentions or instances of the word "acceptance."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "acceptance."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lan
    -0.73
     Kun
    -0.66
    pots
    -0.65
     Orn
    -0.63
     Rove
    -0.61
    stones
    -0.60
     Terr
    -0.60
    semble
    -0.59
    zone
    -0.59
     subdiv
    -0.58
    POSITIVE LOGITS
     acceptance
    3.92
    accept
    1.87
     acknowledgement
    1.86
     rejection
    1.84
     accepting
    1.82
     acknowledgment
    1.72
     Accept
    1.71
     accept
    1.65
     adoption
    1.63
     approval
    1.56
    Act Density 0.013%

    No Known Activations