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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating laying the groundwork or preparation for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating upcoming events or conditions that set a context for future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heart
    -0.84
    ãĥij
    -0.80
    é¾
    -0.76
    cles
    -0.72
    mask
    -0.71
    ynski
    -0.68
    agar
    -0.67
    mare
    -0.66
    loo
    -0.66
    ibble
    -0.65
    POSITIVE LOGITS
    geries
    1.09
    gery
    0.89
    bidden
    0.81
     starters
    0.77
    aging
    0.71
     settlements
    0.68
     passage
    0.68
    wards
    0.68
     instance
    0.67
     verification
    0.66
    Act Density 0.157%

    No Known Activations