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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions and obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vero
    -0.17
     carne
    -0.15
    igure
    -0.14
    å§ī
    -0.14
    afil
    -0.14
     nl
    -0.14
    emale
    -0.14
     اÙĦÙħÙĤ
    -0.14
     tower
    -0.13
    iglia
    -0.13
    POSITIVE LOGITS
    ncpy
    0.16
     UINavigationController
    0.15
    _IE
    0.15
    год
    0.15
    afort
    0.14
    کا
    0.14
    ofday
    0.14
    _GRP
    0.14
     Lob
    0.14
     æ½
    0.14
    Act Density 0.082%

    No Known Activations