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

    Neuronpedia

    INDEX
    Explanations

    references to discussions or thoughts about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omat
    -0.17
    arl
    -0.14
    hor
    -0.14
    birth
    -0.14
    ìī¬
    -0.14
    sports
    -0.13
    utf
    -0.13
    unity
    -0.13
    issen
    -0.13
     Canter
    -0.13
    POSITIVE LOGITS
     yard
    0.17
    ombat
    0.16
    abd
    0.15
    ogne
    0.14
     exact
    0.14
    obe
    0.14
    upert
    0.14
    cks
    0.14
     Jeh
    0.13
    eno
    0.13
    Act Density 0.004%

    No Known Activations