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

    Neuronpedia

    INDEX
    Explanations

    prolific connectivity terms and initials denoting people and characters

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "A.K." or similar characters within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.85
     guiActiveUn
    -0.69
    ordan
    -0.68
    kefeller
    -0.67
    theless
    -0.63
     applic
    -0.58
    phony
    -0.58
    vironment
    -0.57
    natureconservancy
    -0.57
    fiction
    -0.56
    POSITIVE LOGITS
    ikuman
    0.81
    chuk
    0.72
    lie
    0.65
    Õ
    0.65
     Rowling
    0.64
    ucha
    0.64
    Lago
    0.64
    adesh
    0.62
     Hutch
    0.62
    riel
    0.61
    Act Density 0.091%

    No Known Activations