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

    Neuronpedia

    INDEX
    Explanations

    words referring to specific people or characters

    oai_token-act-pair · gpt-3.5-turbo

    the word "whom" in various contexts indicating relationships or references to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pad
    -0.72
    roads
    -0.71
    termin
    -0.67
    reth
    -0.65
    construct
    -0.63
    bard
    -0.61
    ply
    -0.61
    ricks
    -0.61
    starting
    -0.60
    Tokens
    -0.60
    POSITIVE LOGITS
    soever
    2.05
     whom
    0.74
    izens
    0.72
     Allaah
    0.71
    nown
    0.71
    owship
    0.69
    selves
    0.67
    edIn
    0.66
     Pulitzer
    0.65
     dearly
    0.64
    Act Density 0.020%

    No Known Activations