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

    Neuronpedia

    INDEX
    Explanations

    phrases related to entering or initiating actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KeepAlive
    -0.50
    ma
    -0.49
     đãi
    -0.48
     vone
    -0.47
    ấy
    -0.45
    7
    -0.45
    ama
    -0.44
    fun
    -0.44
    策
    -0.44
     Pue
    -0.43
    POSITIVE LOGITS
     into
    1.64
     INTO
    1.62
     Into
    1.57
    Into
    1.56
    INTO
    1.38
     Entering
    1.35
     entered
    1.31
     enters
    1.30
     entering
    1.30
    Entering
    1.29
    Act Density 0.246%

    No Known Activations