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

    Neuronpedia

    INDEX
    Explanations

    direct quotations or statements made by someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the act of speaking or sharing opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STD
    -0.71
    omin
    -0.69
    few
    -0.69
    cult
    -0.68
    xtap
    -0.68
    sbm
    -0.68
    Rare
    -0.66
    icut
    -0.66
    pes
    -0.65
    existent
    -0.64
    POSITIVE LOGITS
     goodbye
    0.89
    iveness
    0.66
     sweetness
    0.65
    ario
    0.64
    erous
    0.64
    oline
    0.60
     hello
    0.60
    eness
    0.60
    arial
    0.60
    ieu
    0.59
    Act Density 0.039%

    No Known Activations