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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce an example or provide clarification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.79
    aughs
    -0.77
    OGR
    -0.74
    abwe
    -0.71
    ãĥ´
    -0.70
    emis
    -0.70
    folios
    -0.70
    atched
    -0.69
    acco
    -0.67
    ambo
    -0.67
    POSITIVE LOGITS
     goodbye
    0.91
     hello
    0.81
    ings
    0.72
    volent
    0.71
    lihood
    0.70
    y
    0.69
    ies
    0.69
     hi
    0.67
    yer
    0.67
    ansky
    0.65
    Act Density 0.044%

    No Known Activations