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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to APIs and integration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аÑĢÑĩ
    -0.16
    éĭ
    -0.14
     Schiff
    -0.14
     geo
    -0.13
    ambre
    -0.13
     Willis
    -0.13
    arrass
    -0.13
    isay
    -0.13
    uggy
    -0.13
     Starr
    -0.13
    POSITIVE LOGITS
     secret
    0.35
     Secret
    0.35
    Secret
    0.32
    secret
    0.30
    _secret
    0.30
    -secret
    0.29
     secrets
    0.28
     SECRET
    0.28
     secre
    0.28
    ç§ĺ
    0.27
    Act Density 0.085%

    No Known Activations