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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and expressions of distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.24
    unter
    -0.21
    Ñı
    -0.19
    a
    -0.18
    inx
    -0.16
    ÑĤого
    -0.16
    d
    -0.16
    y
    -0.16
    e
    -0.15
    ussian
    -0.15
    POSITIVE LOGITS
    /-
    0.20
    wards
    0.18
    webkit
    0.15
    rc
    0.15
    ness
    0.15
    ting
    0.15
    wealth
    0.14
    urile
    0.14
    vest
    0.14
    etheless
    0.14
    Act Density 0.215%

    No Known Activations