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

    Neuronpedia

    INDEX
    Explanations

    references to truth, knowledge, and understanding in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heap
    -0.15
    äter
    -0.14
    dbh
    -0.13
    aney
    -0.13
    ắt
    -0.13
    .poi
    -0.13
    duit
    -0.13
    //{{
    -0.13
    ë´ī
    -0.13
     experiences
    -0.12
    POSITIVE LOGITS
     true
    0.50
     extent
    0.40
    true
    0.38
     identity
    0.36
     TRUE
    0.33
     meaning
    0.32
     exact
    0.32
    extent
    0.32
    identity
    0.30
     identities
    0.30
    Act Density 0.199%

    No Known Activations