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

    Neuronpedia

    INDEX
    Explanations

    negative evaluations of content or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agen
    -0.15
    окÑĥ
    -0.14
    duk
    -0.14
     soften
    -0.14
    alse
    -0.14
    du
    -0.14
    Âłmiles
    -0.14
    tape
    -0.14
    -xs
    -0.13
     Charlottesville
    -0.13
    POSITIVE LOGITS
     sino
    0.15
     Punch
    0.15
     Hole
    0.14
    indre
    0.14
     hole
    0.14
    PCP
    0.14
     Animalia
    0.14
    åı·
    0.14
    ût
    0.14
    à¤ķन
    0.14
    Act Density 0.125%

    No Known Activations