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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visibility or something being partially concealed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inea
    -0.17
    orum
    -0.14
    ÙĬب
    -0.14
    &a
    -0.14
    atisfaction
    -0.13
    clare
    -0.13
    REET
    -0.13
    ucs
    -0.13
     Randall
    -0.13
    reet
    -0.13
    POSITIVE LOGITS
    locs
    0.16
    utow
    0.16
    ockets
    0.15
    antino
    0.15
     TMPro
    0.15
    odont
    0.15
    ndx
    0.14
    ropa
    0.14
    _WR
    0.14
    ighton
    0.14
    Act Density 0.108%

    No Known Activations