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

    Neuronpedia

    INDEX
    Explanations

    references to the majority or most common occurrences in a given context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "most."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.74
    pless
    -0.72
    rompt
    -0.70
     CARD
    -0.66
    pton
    -0.65
     guiActiveUnfocused
    -0.62
    thur
    -0.62
    arium
    -0.61
    pt
    -0.60
     LOT
    -0.60
    POSITIVE LOGITS
     importantly
    1.06
     Helpful
    0.94
     Wanted
    0.89
    entimes
    0.86
     Likely
    0.85
     Important
    0.84
     important
    0.83
    likely
    0.81
     notable
    0.79
    body
    0.78
    Act Density 0.039%

    No Known Activations