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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removing or taking off items or obligations

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

    takeoff and flight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -------
    -0.57
    olateral
    -0.46
    errorMsg
    -0.43
    warnai
    -0.42
     $_[
    -0.40
     satisfe
    -0.39
    DBMS
    -0.38
     sécurisé
    -0.38
     חיצוניים
    -0.37
    groet
    -0.36
    POSITIVE LOGITS
     takeoff
    1.11
     Biôgrafia
    0.59
     flight
    0.57
     flying
    0.53
    الدراسه
    0.52
     FLY
    0.51
     Flight
    0.49
    ToRemove
    0.49
     flies
    0.48
     leap
    0.48
    Act Density 0.002%

    No Known Activations