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

    Neuronpedia

    INDEX
    Explanations

    action verbs combined with prepositions indicating a location or direction

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating action or activities that involve decision-making or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uum
    -0.77
     ][
    -0.67
    unity
    -0.67
    avin
    -0.65
    ortium
    -0.64
    blogspot
    -0.64
    cens
    -0.62
    elsius
    -0.61
    chev
    -0.60
    intention
    -0.60
    POSITIVE LOGITS
     alike
    1.00
     accordingly
    0.81
    instead
    0.74
     anew
    0.72
     prest
    0.69
     consequently
    0.69
    nob
    0.62
     ourselves
    0.62
     thereafter
    0.61
     whichever
    0.61
    Act Density 0.359%

    No Known Activations