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

    Neuronpedia

    INDEX
    Explanations

    short phrases or sentences focused on specific actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tack
    -0.72
    NetMessage
    -0.72
    "?
    -0.64
     anyway
    -0.64
    .</
    -0.63
     hug
    -0.61
     ain
    -0.61
     quir
    -0.60
     suspic
    -0.60
     extinct
    -0.60
    POSITIVE LOGITS
     Whilst
    1.88
     Firstly
    1.55
     Initially
    1.48
     However
    1.38
     While
    1.36
     This
    1.35
     Although
    1.31
     These
    1.30
     During
    1.30
     Specifically
    1.29
    Act Density 0.565%

    No Known Activations