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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to possession or belonging

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related possessive terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ominated
    -0.73
    ifact
    -0.72
    ographers
    -0.66
    uph
    -0.65
    otin
    -0.64
    otation
    -0.64
    yip
    -0.64
    verb
    -0.64
    ulas
    -0.63
    daq
    -0.62
    POSITIVE LOGITS
     midst
    1.27
     own
    1.20
     stead
    1.20
     entirety
    1.18
     vicinity
    1.14
     guise
    1.03
     stride
    1.02
     infancy
    1.00
     footsteps
    0.98
     wake
    0.95
    Act Density 0.135%

    No Known Activations