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

    Neuronpedia

    INDEX
    Explanations

    terms related to negation or absence in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agna
    -0.15
    uropean
    -0.15
    TINGS
    -0.14
    çŃĭ
    -0.14
    isdiction
    -0.14
    borough
    -0.14
    uiltin
    -0.14
    Fal
    -0.14
     stranger
    -0.14
    typeid
    -0.14
    POSITIVE LOGITS
    ary
    0.20
    ihan
    0.18
    quam
    0.15
    oes
    0.15
    umber
    0.15
    ष
    0.14
     implemented
    0.14
    ames
    0.13
    ick
    0.13
    si
    0.13
    Act Density 0.032%

    No Known Activations