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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by adjectives

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypes
    -0.76
    witch
    -0.69
    eers
    -0.66
     Malf
    -0.66
     Toggle
    -0.65
    wat
    -0.65
    inx
    -0.65
    load
    -0.63
    /-
    -0.63
    VERTIS
    -0.63
    POSITIVE LOGITS
     midst
    1.34
     own
    1.26
     vicinity
    1.18
     guise
    1.16
     stride
    1.15
     estimation
    1.02
     backyard
    1.00
     stead
    0.97
     manner
    0.95
     surroundings
    0.95
    Act Density 0.147%

    No Known Activations