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

    Neuronpedia

    INDEX
    Explanations

    words related to being unwanted or undesirable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignKey
    -0.07
    sein
    -0.07
    aeper
    -0.07
    senal
    -0.07
    ýš
    -0.07
    stagram
    -0.07
    point
    -0.06
    bero
    -0.06
    tempts
    -0.06
    zon
    -0.06
    POSITIVE LOGITS
     unw
    0.06
     Uns
    0.06
    wel
    0.06
    owell
    0.06
     Coil
    0.06
    emachine
    0.06
    izza
    0.06
    ingt
    0.06
    ly
    0.06
    Įĵ
    0.06
    Act Density 0.001%

    No Known Activations