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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing agreement or understanding

    oai_token-act-pair · gpt-3.5-turbo

    the word "totally" and its variations used for emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.79
    rers
    -0.79
    llor
    -0.78
    liest
    -0.76
    åº
    -0.75
    ulative
    -0.74
    mere
    -0.74
    lest
    -0.70
    ourses
    -0.70
    ently
    -0.68
    POSITIVE LOGITS
     obliter
    0.73
     unrelated
    0.72
    heartedly
    0.68
    STAR
    0.67
     annihil
    0.67
    ect
    0.64
    allo
    0.64
    ove
    0.63
     und
    0.63
    ogen
    0.63
    Act Density 0.012%

    No Known Activations