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

    Neuronpedia

    INDEX
    Explanations

    elements related to critique or negative opinions about experiences or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letic
    -0.15
    adc
    -0.15
    wn
    -0.15
    ourt
    -0.15
     sobie
    -0.14
    çĮ®
    -0.14
    odd
    -0.14
    fy
    -0.14
     Celt
    -0.13
    ely
    -0.13
    POSITIVE LOGITS
    #__
    0.17
    essim
    0.15
    oning
    0.15
    uhn
    0.14
    GetY
    0.14
    à¤¿à¤ľà¤¨
    0.14
    okus
    0.13
    oming
    0.13
    aser
    0.13
    adir
    0.13
    Act Density 0.312%

    No Known Activations