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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to forceful physical impact or destruction

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "smash" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redo
    -0.74
    vernment
    -0.70
    ussen
    -0.64
    rog
    -0.64
    ogo
    -0.64
    zl
    -0.63
    umatic
    -0.63
     lawy
    -0.63
    adapt
    -0.61
    isan
    -0.61
    POSITIVE LOGITS
    dragon
    0.73
     dreams
    0.72
    jj
    0.67
    llah
    0.66
    vier
    0.66
    itational
    0.65
     goodbye
    0.65
    IGHT
    0.65
     crush
    0.63
     Mouth
    0.62
    Act Density 0.073%

    No Known Activations