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

    Neuronpedia

    INDEX
    Explanations

    objects or equipment that are either destroyed or transformed

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceed
    -0.73
    egal
    -0.72
    heit
    -0.71
    gres
    -0.70
    enthal
    -0.70
    zee
    -0.69
    verting
    -0.68
    ornia
    -0.68
    corn
    -0.67
    blast
    -0.67
    POSITIVE LOGITS
     belonging
    0.75
     belongings
    0.73
    arium
    0.73
     resembling
    0.72
    ivity
    0.71
    ry
    0.69
    afort
    0.69
     objects
    0.69
     manufacturer
    0.68
    uria
    0.68
    Act Density 1.204%

    No Known Activations