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

    Neuronpedia

    INDEX
    Explanations

    phrases representing comparison, evaluation, or connection

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that contain structural or comparative elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.74
    -,
    -0.72
    ãĥ¥
    -0.69
    cellaneous
    -0.68
    ļéĨĴ
    -0.67
    ////////////////
    -0.67
    Includes
    -0.65
    OTHER
    -0.64
    ,...
    -0.64
    Winged
    -0.63
    POSITIVE LOGITS
     however
    1.33
     though
    1.17
     it
    0.96
     although
    0.88
     therefore
    0.86
     there
    0.84
     we
    0.83
     this
    0.81
     moreover
    0.78
     they
    0.78
    Act Density 0.263%

    No Known Activations