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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and expressions of inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ael
    -0.16
    rong
    -0.15
    urg
    -0.14
    radius
    -0.14
    intColor
    -0.14
    à¤ķरण
    -0.14
    ruz
    -0.14
    reh
    -0.14
    uy
    -0.13
    EncodingException
    -0.13
    POSITIVE LOGITS
     portions
    0.22
     portion
    0.20
    avo
    0.17
     everyone
    0.15
    AMED
    0.14
    illions
    0.14
     majority
    0.14
    iband
    0.14
     Portions
    0.14
     material
    0.14
    Act Density 0.352%

    No Known Activations