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

    Neuronpedia

    INDEX
    Explanations

    phrases related to choices and decision-making processes

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

    Follows "cause", "new", or a symbol

    np_acts-logits-general · gemini-2.0-flash

    choices cause pain or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.70
    ETRIC
    -0.62
     riuscito
    -0.60
     apocalypse
    -0.59
    нский
    -0.57
     notamment
    -0.57
     Hooper
    -0.57
    __(/*!
    -0.56
    wpi
    -0.56
    \|_{
    -0.56
    POSITIVE LOGITS
    autique
    0.52
     circonstances
    0.52
     defaultstate
    0.48
    vaadin
    0.46
    ḷ
    0.46
     autorytatywna
    0.45
     mentale
    0.44
     gynhyrchwyd
    0.42
    Parcelize
    0.41
     energética
    0.41
    Act Density 0.250%

    No Known Activations