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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases indicating conditions, expectations, or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #ae
    -0.16
    -fontawesome
    -0.15
     gul
    -0.15
    缴
    -0.14
    imb
    -0.14
    orton
    -0.14
    zed
    -0.14
    zej
    -0.14
    reau
    -0.14
    _framework
    -0.14
    POSITIVE LOGITS
     thy
    0.19
    ignon
    0.17
    athy
    0.14
    ÑĦик
    0.14
    asta
    0.14
    arp
    0.14
     Thy
    0.14
     DBG
    0.14
    isci
    0.14
     Ðijез
    0.14
    Act Density 0.194%

    No Known Activations