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

    Neuronpedia

    INDEX
    Explanations

    titles of movies or music in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.78
    ife
    -0.70
    mares
    -0.70
    senal
    -0.70
    ason
    -0.69
    thur
    -0.68
    mber
    -0.67
    cha
    -0.65
    ĻĤ
    -0.64
    acas
    -0.63
    POSITIVE LOGITS
    /"
    0.87
    SPONSORED
    0.81
     referring
    0.79
     meaning
    0.77
     implying
    0.75
     aka
    0.74
     according
    0.71
     referencing
    0.71
     which
    0.70
     whereby
    0.69
    Act Density 0.090%

    No Known Activations