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

    Neuronpedia

    INDEX
    Explanations

    phrases related to prevention or stopping actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     muualla
    -0.71
    ItemBackground
    -0.70
     ComVisible
    -0.66
     للاسماء
    -0.64
    IsMutable
    -0.64
    sonian
    -0.64
     Infórmanos
    -0.63
    rungsseite
    -0.61
     autorytatywna
    -0.61
     Taktlose
    -0.60
    POSITIVE LOGITS
     from
    1.07
     access
    0.77
    from
    0.70
    access
    0.65
     prevent
    0.65
     Zugriff
    0.63
     progress
    0.62
     FROM
    0.61
     Prevent
    0.61
     от
    0.61
    Act Density 0.245%

    No Known Activations