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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing negative outcomes or unfortunate situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollapsed
    -0.16
    cono
    -0.15
    Äįka
    -0.15
    swick
    -0.14
    innacle
    -0.14
    bedo
    -0.14
     wonder
    -0.14
    czy
    -0.14
    ünk
    -0.14
    ont
    -0.13
    POSITIVE LOGITS
    ably
    0.23
    iteral
    0.17
    omik
    0.15
    omas
    0.15
    -looking
    0.14
    istan
    0.14
    /un
    0.14
    mente
    0.14
    CTS
    0.14
    -hero
    0.14
    Act Density 0.015%

    No Known Activations