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

    Neuronpedia

    INDEX
    Explanations

    elements related to account verification and registration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    imperative or command verb forms across multiple languages.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     ένας
    -0.72
     besonderer
    -0.61
    entlicher
    -0.60
     guter
    -0.60
     Glaube
    -0.60
     derselbe
    -0.59
     großer
    -0.59
     hoher
    -0.59
     duża
    -0.57
     eigener
    -0.57
    POSITIVE LOGITS
    기를
    0.92
     את
    0.87
    지를
    0.81
     einen
    0.81
    리를
    0.77
     ואת
    0.76
     را
    0.73
    einen
    0.72
    点を
    0.66
    数を
    0.65
    Act Density 0.036%

    No Known Activations