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

    Neuronpedia

    INDEX
    Explanations

    dialogue punctuated with actions and character interactions

    oai_token-act-pair · gpt-3.5-turbo

    dialogue exchanges and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUM
    -0.73
    taboola
    -0.71
     respectively
    -0.70
    ansky
    -0.68
    dayName
    -0.65
    represented
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
     Surviv
    -0.65
     converge
    -0.64
    Ń·
    -0.64
    POSITIVE LOGITS
     Sirius
    0.86
     Merlin
    0.84
     Dumbledore
    0.81
    erva
    0.80
     kisses
    0.80
    âĶĢâĶĢ
    0.79
     Weasley
    0.77
    yss
    0.77
     Hermione
    0.77
     Scorp
    0.76
    Act Density 0.994%

    No Known Activations