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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Too" with a strong match

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.71
    craft
    -0.71
    inarily
    -0.67
    anwhile
    -0.64
    issance
    -0.63
    icipated
    -0.63
    hyde
    -0.63
    ords
    -0.61
    iens
    -0.59
     1886
    -0.58
    POSITIVE LOGITS
     much
    0.83
     busy
    0.79
     afraid
    0.77
    ls
    0.77
     far
    0.76
    oths
    0.75
     lax
    0.73
     distracting
    0.70
     tempting
    0.69
    Much
    0.69
    Act Density 1.991%

    No Known Activations