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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal admissions of guilt and guilty pleas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    lacak
    -0.15
    illions
    -0.14
    leans
    -0.14
    thy
    -0.14
    AKE
    -0.14
    одо
    -0.13
    ÏģÏį
    -0.13
    ç¬
    -0.13
    edium
    -0.13
    POSITIVE LOGITS
    isman
    0.19
    verted
    0.16
    999
    0.16
    æĻ´
    0.15
    585
    0.15
    ess
    0.14
    ub
    0.14
    itar
    0.14
     MO
    0.14
    owl
    0.14
    Act Density 0.009%

    No Known Activations