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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or phrases with a particular emphasis or sentiment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people or characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hots
    -0.82
    Roaming
    -0.69
    ãĥĻ
    -0.68
     Soc
    -0.68
    milo
    -0.66
     âľ
    -0.65
    razil
    -0.65
    otes
    -0.65
     Reese
    -0.63
    Software
    -0.62
    POSITIVE LOGITS
    d
    1.15
    dl
    1.11
    dor
    0.98
    dt
    0.98
    die
    0.97
    Ds
    0.95
    dL
    0.94
    dal
    0.93
    dh
    0.92
    rod
    0.92
    Act Density 0.243%

    No Known Activations