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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causal relationships and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aro
    -0.16
    issen
    -0.15
    cale
    -0.15
    rag
    -0.15
    ht
    -0.15
    amm
    -0.14
    ict
    -0.14
    rat
    -0.14
    cken
    -0.14
    ander
    -0.14
    POSITIVE LOGITS
    spd
    0.16
    viewController
    0.16
    Ïħνα
    0.15
    eyh
    0.15
    edik
    0.15
    íĻĢ
    0.14
    raç
    0.14
    çĥĪ
    0.14
    alach
    0.14
    dbh
    0.14
    Act Density 0.056%

    No Known Activations