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

    Neuronpedia

    INDEX
    Explanations

    the word "whoever" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to people or entities of unspecified identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.79
    enberg
    -0.76
    enthal
    -0.75
     Mount
    -0.73
    Loading
    -0.72
     Shield
    -0.68
     Brief
    -0.67
     Range
    -0.66
    South
    -0.66
    âĨ
    -0.65
    POSITIVE LOGITS
    soever
    1.43
    omever
    1.13
     else
    1.08
     whoever
    0.98
    oshop
    0.97
    etheless
    0.93
     nomine
    0.90
    ichever
    0.89
    DragonMagazine
    0.87
    swer
    0.87
    Act Density 0.004%

    No Known Activations