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

    Neuronpedia

    INDEX
    Explanations

    discussions about personal choices and preferences

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

    Following a decision or preference

    np_acts-logits-general · gemini-2.0-flash

    choosing and preferring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.67
     informée
    -0.54
     zelve
    -0.54
    ="$(
    -0.53
     öffnungszeiten
    -0.53
    arrête
    -0.53
     eenige
    -0.52
    Xna
    -0.52
    motive
    -0.51
     milliers
    -0.51
    POSITIVE LOGITS
     opting
    1.29
     opted
    1.29
     opt
    1.21
     prefer
    1.16
     preferring
    1.14
     opts
    1.13
     chose
    1.06
     prefers
    1.04
     choose
    1.03
     optar
    1.03
    Act Density 0.466%

    No Known Activations