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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive determiners along with words related to physical actions or states

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozy
    -0.85
     Izan
    -0.81
    liest
    -0.76
    rano
    -0.74
    nown
    -0.73
     imaginable
    -0.71
     Lyndon
    -0.69
    endix
    -0.69
     resembling
    -0.68
    forth
    -0.67
    POSITIVE LOGITS
     own
    1.16
     feet
    1.14
     noses
    1.11
     mouths
    1.04
     emotions
    1.02
     fingers
    1.01
     ears
    0.99
     ducks
    0.98
     asses
    0.98
     toes
    0.98
    Act Density 0.141%

    No Known Activations