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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific toy or fictional construct called "GoBots."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific toy lines or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intimid
    -0.75
     livest
    -0.69
     awa
    -0.68
    vid
    -0.66
     streng
    -0.64
     skelet
    -0.64
    ŃĶ
    -0.64
    issance
    -0.63
    Versions
    -0.62
     abduct
    -0.62
    POSITIVE LOGITS
    wana
    1.18
    nikov
    1.12
    rons
    0.97
    anu
    0.97
    uba
    0.97
    assium
    0.96
    heet
    0.95
    hips
    0.88
    rans
    0.86
    chens
    0.85
    Act Density 0.015%

    No Known Activations