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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions involving body parts

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to personal belongings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.76
    soever
    -0.74
    orously
    -0.70
    locked
    -0.66
     Matter
    -0.65
    ãĤ§
    -0.65
     Typhoon
    -0.64
    ved
    -0.64
     Span
    -0.62
     Else
    -0.62
    POSITIVE LOGITS
     sake
    1.11
     reasons
    0.83
     forgiveness
    0.80
    ummies
    0.78
    ulz
    0.76
    EMOTE
    0.76
     jug
    0.74
     inspiration
    0.74
     immortality
    0.73
     elusive
    0.70
    Act Density 0.392%

    No Known Activations