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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical interaction or hands-on experience

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating hands-on experiences or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uct
    -0.72
    opl
    -0.65
    reg
    -0.65
     Reasons
    -0.63
    anon
    -0.63
    stories
    -0.63
    mal
    -0.63
    Tex
    -0.62
    rities
    -0.61
    edu
    -0.61
    POSITIVE LOGITS
    esome
    0.84
    manship
    0.76
    ledged
    0.69
    eton
    0.66
    orest
    0.66
     Nieto
    0.65
    eger
    0.65
    ggle
    0.64
     attitude
    0.62
    awei
    0.62
    Act Density 0.055%

    No Known Activations