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

    Neuronpedia

    INDEX
    Explanations

    phrases related to posting, sharing, announcing, and other forms of communication or dissemination of information

    oai_token-act-pair · gpt-3.5-turbo

    actions related to the distribution or announcement of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugal
    -0.68
    pires
    -0.64
    humans
    -0.62
     Sierra
    -0.61
    bara
    -0.61
     arisen
    -0.60
    ses
    -0.59
    ZI
    -0.58
    si
    -0.58
    luence
    -0.56
    POSITIVE LOGITS
     separately
    0.91
     electronically
    0.88
     accordingly
    0.87
     automatically
    0.87
     individually
    0.83
     consecut
    0.79
     anonymously
    0.79
     jointly
    0.77
     statically
    0.75
     digitally
    0.74
    Act Density 0.284%

    No Known Activations