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

    Neuronpedia

    INDEX
    Explanations

    the root cause or origin of something

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of origin or causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bought
    -0.59
     booked
    -0.59
    oppy
    -0.56
     Preview
    -0.54
    ockets
    -0.54
     Rated
    -0.54
    phis
    -0.54
    istors
    -0.53
     maneu
    -0.53
     Recomm
    -0.53
    POSITIVE LOGITS
     from
    1.16
    from
    1.06
     FROM
    1.02
    From
    0.98
     solely
    0.90
     principally
    0.89
     From
    0.88
     directly
    0.86
     derive
    0.85
     chiefly
    0.80
    Act Density 0.079%

    No Known Activations