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

    Neuronpedia

    INDEX
    Explanations

    references to brackets or similar symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIA
    -0.17
    009
    -0.16
    frei
    -0.15
     luc
    -0.15
    orem
    -0.14
    rame
    -0.14
    moid
    -0.13
     hang
    -0.13
     delegates
    -0.13
    enberg
    -0.13
    POSITIVE LOGITS
    etch
    0.16
    alian
    0.16
    bÃŃr
    0.16
    illion
    0.15
    Sensitive
    0.15
    avou
    0.15
    ï¿¥
    0.14
    du
    0.14
    ed
    0.14
    ols
    0.14
    Act Density 0.007%

    No Known Activations