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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},"
    -0.58
    Jump
    -0.58
    ebin
    -0.57
    uum
    -0.54
    itely
    -0.53
    URE
    -0.53
    Sort
    -0.53
    chairs
    -0.52
    Pretty
    -0.52
    URES
    -0.52
    POSITIVE LOGITS
    ,
    0.94
    ,.
    0.87
    ,...
    0.83
     though
    0.80
     importantly
    0.77
    ,,
    0.76
    :
    0.73
     however
    0.69
    zers
    0.67
    ,—
    0.66
    Act Density 0.076%

    No Known Activations