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

    Neuronpedia

    INDEX
    Explanations

    terms related to automated processes and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    radient
    -0.18
    azu
    -0.16
    zet
    -0.16
    каÑģ
    -0.16
    rant
    -0.15
    Instructions
    -0.15
    ioneer
    -0.14
    ãĤ¸
    -0.14
     hâl
    -0.14
     BaseEntity
    -0.14
    POSITIVE LOGITS
     automatically
    0.44
     automatic
    0.38
     Automatically
    0.34
     ìŀIJëıĻ
    0.32
     Automatic
    0.31
    automatic
    0.30
     automáticamente
    0.30
    Automatic
    0.30
    èĩªåĬ¨
    0.28
    èĩªåĭķ
    0.28
    Act Density 0.157%

    No Known Activations