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

    Neuronpedia

    INDEX
    Explanations

    requests or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbnail
    -0.67
    were
    -0.63
     LAT
    -0.62
     Current
    -0.61
    transfer
    -0.59
    ociate
    -0.58
    onic
    -0.58
    udi
    -0.58
     Maver
    -0.58
     bachelor
    -0.57
    POSITIVE LOGITS
     raining
    1.10
     impossible
    1.02
     easier
    1.00
     easy
    0.91
     prudent
    0.90
     unclear
    0.87
     advisable
    0.85
     difficult
    0.83
     worthwhile
    0.80
     harder
    0.79
    Act Density 0.081%

    No Known Activations