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

    Neuronpedia

    INDEX
    Explanations

    characters/characters names and locations

    oai_token-act-pair · gpt-3.5-turbo

    themes related to personal experiences and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rehensive
    -0.91
    cedented
    -0.91
    Already
    -0.91
    Laun
    -0.87
    alyst
    -0.86
    atform
    -0.81
    aughlin
    -0.78
    jri
    -0.77
     rollout
    -0.77
    Developer
    -0.76
    POSITIVE LOGITS
     Buddhism
    1.34
     homosexuality
    1.32
     polygamy
    1.21
     pronouns
    1.19
     vampires
    1.18
     feminism
    1.16
     witchcraft
    1.14
     Christianity
    1.13
     masturbation
    1.13
     atheism
    1.12
    Act Density 0.533%

    No Known Activations