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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.20
    ry
    -0.17
    796
    -0.16
    anye
    -0.15
    缮
    -0.15
    dle
    -0.15
    arp
    -0.15
    adget
    -0.14
    atisf
    -0.14
    alaria
    -0.14
    POSITIVE LOGITS
    iative
    0.21
    iable
    0.20
    acher
    0.19
    ably
    0.19
    ately
    0.18
    iat
    0.18
    ãĥ¥
    0.17
    iate
    0.17
    iates
    0.17
    iser
    0.16
    Act Density 0.014%

    No Known Activations