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

    Neuronpedia

    INDEX
    Explanations

    themes related to storytelling, blending elements of different genres or styles to create new narratives

    oai_token-act-pair · gpt-3.5-turbo

    combinations of humor and storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Otherwise
    -0.61
    ©¶æ¥µ
    -0.59
    stadt
    -0.59
    redo
    -0.55
    itary
    -0.55
     Accessed
    -0.53
     subsequent
    -0.52
     unmarked
    -0.52
     doubtful
    -0.52
    amaz
    -0.51
    POSITIVE LOGITS
     into
    1.14
     with
    0.97
    into
    0.93
     seamlessly
    0.88
     together
    0.86
    with
    0.85
     onto
    0.82
     elements
    0.82
     genres
    0.79
     disparate
    0.78
    Act Density 0.234%

    No Known Activations