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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making plans or decisions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    However
    -0.76
     However
    -0.75
    butt
    -0.74
    But
    -0.72
     But
    -0.70
    oba
    -0.69
    idon
    -0.66
    hex
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    è£ħ
    -0.61
    POSITIVE LOGITS
     nonetheless
    0.99
     namely
    0.97
     especially
    0.79
     owing
    0.79
     according
    0.78
    especially
    0.76
     particularly
    0.72
    particularly
    0.72
     anyway
    0.72
     insofar
    0.70
    Act Density 0.338%

    No Known Activations