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

    Neuronpedia

    INDEX
    Explanations

    words expressing disappointment or sadness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĮ
    -0.15
    hoff
    -0.14
    اÙĨÙĩ
    -0.14
    addtogroup
    -0.13
    umper
    -0.13
    hp
    -0.13
    warz
    -0.13
     Finder
    -0.13
    -0.13
     assert
    -0.13
    POSITIVE LOGITS
    heart
    0.30
    pir
    0.29
    concert
    0.28
    orient
    0.27
    appoint
    0.27
    astr
    0.26
    ench
    0.26
    illusion
    0.25
    appointed
    0.24
    oriented
    0.24
    Act Density 0.015%

    No Known Activations