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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "plan" and related concepts of planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okud
    -0.15
    Ñıж
    -0.14
    bild
    -0.14
     turno
    -0.14
    ungs
    -0.14
    utom
    -0.14
    nds
    -0.14
     NavParams
    -0.14
    ULSE
    -0.14
    éIJĺ
    -0.14
    POSITIVE LOGITS
     ahead
    0.35
     accordingly
    0.29
     Ahead
    0.29
    ahead
    0.28
    Ahead
    0.27
    -ahead
    0.27
     Accordingly
    0.26
     how
    0.20
     activities
    0.20
     around
    0.19
    Act Density 0.060%

    No Known Activations