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

    Neuronpedia

    INDEX
    Explanations

    words related to various forms of the word "rotate"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "parrot."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.82
    ept
    -0.68
    ufact
    -0.63
    BILITIES
    -0.62
    College
    -0.59
    intosh
    -0.59
     conscious
    -0.59
    ħĭ
    -0.59
     quarters
    -0.58
     cumbers
    -0.58
    POSITIVE LOGITS
    rot
    0.97
    ting
    0.89
    omy
    0.89
    ica
    0.86
    ations
    0.86
    ation
    0.85
    iful
    0.83
    ational
    0.82
    oscope
    0.82
    chet
    0.81
    Act Density 0.007%

    No Known Activations