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

    Neuronpedia

    INDEX
    Explanations

    occurrences of certain special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lyft
    -0.15
     Airbnb
    -0.15
    ãĥ¼ãĥ©
    -0.15
     Rohingya
    -0.14
    WhatsApp
    -0.14
     Brexit
    -0.14
    aaS
    -0.14
     Huawei
    -0.14
    ifax
    -0.14
    tual
    -0.14
    POSITIVE LOGITS
     Strong
    0.46
     Hom
    0.40
    Strong
    0.39
     strong
    0.34
    Hom
    0.32
     hom
    0.30
     SB
    0.30
    strong
    0.30
    -strong
    0.29
     sb
    0.27
    Act Density 0.004%

    No Known Activations