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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases that indicate similarity or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzi
    -0.18
    ogan
    -0.17
    ntag
    -0.16
    uv
    -0.15
    ion
    -0.15
     Speaking
    -0.15
    untas
    -0.15
    REFIX
    -0.14
    ing
    -0.14
    issement
    -0.14
    POSITIVE LOGITS
     nhau
    0.20
     throughout
    0.17
    modulo
    0.15
    دÙĬد
    0.15
    iator
    0.15
    Å¡it
    0.14
    FORMAT
    0.14
     gere
    0.14
     across
    0.14
     except
    0.13
    Act Density 0.028%

    No Known Activations