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

    Neuronpedia

    INDEX
    Explanations

    comparative terms related to quantity or size

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Inoltre
    -0.60
    jgl
    -0.60
    Abbiamo
    -0.59
    CrossOrigin
    -0.57
    RemoveField
    -0.54
    FlatAppearance
    -0.54
    contentPadding
    -0.53
    Fatalf
    -0.52
    InitStructure
    -0.51
    Allora
    -0.51
    POSITIVE LOGITS
     cleanest
    0.98
     heaviest
    0.98
     slowest
    0.97
     widest
    0.97
     freshest
    0.97
     wisest
    0.97
     loudest
    0.96
     healthiest
    0.95
     lightest
    0.92
     saddest
    0.91
    Act Density 0.141%

    No Known Activations