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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the act of causing or resulting in an effect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isen
    -0.16
    cken
    -0.16
    gi
    -0.16
    hz
    -0.16
    sets
    -0.15
    ts
    -0.15
    coming
    -0.15
    otate
    -0.15
    ÅĻ
    -0.15
    jam
    -0.15
    POSITIVE LOGITS
    fully
    0.15
    ëģĶ
    0.15
    urdu
    0.15
    /umd
    0.14
    umer
    0.14
    -effect
    0.14
    /ca
    0.14
    ellung
    0.14
    ekli
    0.14
     MetroFramework
    0.13
    Act Density 0.048%

    No Known Activations