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

    Neuronpedia

    INDEX
    Explanations

    negative aspects or criticisms associated with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignon
    -0.18
     posing
    -0.15
     Pose
    -0.15
    pose
    -0.15
    ÃĹ↵↵
    -0.14
     posterior
    -0.14
    ongs
    -0.14
     pend
    -0.14
    ÙĦØŃ
    -0.14
    656
    -0.14
    POSITIVE LOGITS
    uman
    0.15
    /null
    0.15
    (Border
    0.14
    alink
    0.14
     Angeles
    0.14
    ãģ¨ãĤĤ
    0.14
    nop
    0.14
     Samar
    0.14
    ipel
    0.13
    åĴ²
    0.13
    Act Density 0.432%

    No Known Activations