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

    Neuronpedia

    INDEX
    Explanations

    contractions or possessive forms of words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and their variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.75
     Crunch
    -0.67
     Hass
    -0.64
    phabet
    -0.63
    atl
    -0.62
    */(
    -0.62
     misunder
    -0.61
    ancies
    -0.61
    ocobo
    -0.61
     Brus
    -0.59
    POSITIVE LOGITS
     likely
    1.20
     gonna
    1.08
     probably
    1.07
     doomed
    0.98
     liable
    0.97
     surely
    0.96
     definitely
    0.95
     bound
    0.92
     automatically
    0.90
     unlikely
    0.89
    Act Density 0.330%

    No Known Activations