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

    Neuronpedia

    INDEX
    Explanations

    words related to emotional states and attitudes, particularly those that convey unexpectedness or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.17
    prise
    -0.15
    izzo
    -0.14
    enet
    -0.14
     sufficiently
    -0.14
    ascar
    -0.14
    oq
    -0.14
    ноÑģÑĤÑĮÑİ
    -0.14
    tuk
    -0.14
    vailability
    -0.13
    POSITIVE LOGITS
     sounding
    0.48
    -looking
    0.42
     looking
    0.33
    looking
    0.32
    -fe
    0.32
     seeming
    0.30
    -se
    0.29
    istic
    0.27
    ish
    0.27
    ly
    0.27
    Act Density 0.170%

    No Known Activations