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

    Neuronpedia

    INDEX
    Explanations

    words related to validity and approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ander
    -0.17
    enko
    -0.14
    ëĮĢë¡ľ
    -0.14
     freshly
    -0.14
     past
    -0.13
    EN
    -0.13
    _double
    -0.13
    ault
    -0.13
    ANGO
    -0.13
    é¢Ĩ
    -0.13
    POSITIVE LOGITS
    gest
    0.16
    kiem
    0.15
    Ä±ÅŁÄ±k
    0.15
    IRMWARE
    0.15
    erece
    0.14
    eref
    0.14
    CTYPE
    0.14
    kul
    0.14
    ï¼Īå¹³æĪIJ
    0.14
    vens
    0.13
    Act Density 0.010%

    No Known Activations