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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate preparation or setup

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to preparation or positioning for future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sake
    -0.61
     Pastebin
    -0.60
     simplicity
    -0.59
     abstraction
    -0.58
    loss
    -0.57
     cultured
    -0.56
    tein
    -0.55
     denomin
    -0.55
     deduct
    -0.52
     mentioning
    -0.52
    POSITIVE LOGITS
    for
    0.84
     for
    0.84
    entin
    0.77
    Ready
    0.75
     toward
    0.75
    ombo
    0.75
    eele
    0.74
    Against
    0.73
    GGGGGGGG
    0.73
    For
    0.73
    Act Density 0.284%

    No Known Activations