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

    Neuronpedia

    INDEX
    Explanations

    instances where something is resolved, achieved, or changed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "finally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akin
    -0.75
    lav
    -0.72
    pill
    -0.72
    maid
    -0.69
    icipated
    -0.68
    river
    -0.65
    folios
    -0.64
    amide
    -0.64
    tein
    -0.63
     Citation
    -0.63
    POSITIVE LOGITS
     reunited
    1.06
     relent
    0.95
    éĹĺ
    0.84
     reconcil
    0.83
     reun
    0.82
    icably
    0.81
     settle
    0.78
     succeeded
    0.76
    icable
    0.76
     arrived
    0.75
    Act Density 0.030%

    No Known Activations