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

    Neuronpedia

    INDEX
    Explanations

    phrases focusing on assistance and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velte
    -0.16
    หมาย
    -0.16
    jang
    -0.16
    rak
    -0.15
    atchet
    -0.15
    ãģ¹ãģį
    -0.15
    clud
    -0.15
    erge
    -0.14
    naments
    -0.14
    jen
    -0.14
    POSITIVE LOGITS
     us
    0.21
    desk
    0.21
     Äijỡ
    0.17
     me
    0.17
    inton
    0.16
    ÑĢод
    0.15
    esch
    0.15
    lessness
    0.14
    TINGS
    0.14
    roat
    0.14
    Act Density 0.072%

    No Known Activations