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

    Neuronpedia

    INDEX
    Explanations

    names of key characters and their interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.74
    undai
    -0.72
    mens
    -0.71
    ilitation
    -0.71
    raltar
    -0.71
    liga
    -0.68
    PDATE
    -0.67
     industrial
    -0.66
    ailability
    -0.66
    heddar
    -0.65
    POSITIVE LOGITS
     herself
    1.54
     Sparkle
    1.06
     Granger
    1.05
     Fey
    1.04
     Marie
    1.00
     gigg
    0.97
     Mae
    0.96
     Louise
    0.93
     Weasley
    0.92
     Valkyrie
    0.89
    Act Density 0.103%

    No Known Activations