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

    Neuronpedia

    INDEX
    Explanations

    sentences that transition between different topics or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CJ
    -0.81
     ±
    -0.66
     pound
    -0.63
     correct
    -0.60
    ONSORED
    -0.60
     franc
    -0.59
     IPM
    -0.58
     +/-
    -0.58
     cogn
    -0.57
     beans
    -0.57
    POSITIVE LOGITS
    abouts
    1.41
    upon
    1.09
    fore
    0.86
    hovah
    0.80
    ngth
    0.80
     guiActiveUn
    0.78
    olkien
    0.76
    choes
    0.74
     Ukrain
    0.72
    iltr
    0.72
    Act Density 0.147%

    No Known Activations