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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions or reaching agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.77
    Ļ½
    -0.76
    eele
    -0.76
    chance
    -0.74
    nesota
    -0.72
    cean
    -0.71
    ²¾
    -0.71
    »Ĵ
    -0.70
    alde
    -0.70
    emale
    -0.69
    POSITIVE LOGITS
     forth
    1.01
     clean
    0.87
     forward
    0.86
     undone
    0.82
     together
    0.79
     alive
    0.79
     onboard
    0.79
     up
    0.76
     prepared
    0.76
    upp
    0.76
    Act Density 0.050%

    No Known Activations