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

    Neuronpedia

    INDEX
    Explanations

    the word "whom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.08
     <<<<<<<<<<<<<<
    -1.02
    ING
    -0.99
    ing
    -0.99
    ה
    -0.88
    >{@
    -0.88
     Auss
    -0.88
    endregion
    -0.83
    Kariera
    -0.82
    tina
    -0.80
    POSITIVE LOGITS
    Cuánt
    0.94
     whom
    0.82
    erci
    0.82
    ernsey
    0.81
     Goy
    0.79
     Kendal
    0.76
    ffi
    0.75
     Ganes
    0.73
    delaire
    0.72
     Grom
    0.70
    Act Density 0.235%

    No Known Activations