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

    Neuronpedia

    INDEX
    Explanations

    phrases containing a past-tense verb indicating the origin or inception of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conceived" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.73
    ammy
    -0.70
     disg
    -0.64
     Cheong
    -0.62
     reinforcement
    -0.59
     barred
    -0.59
    andra
    -0.59
     unbeaten
    -0.58
     [+
    -0.58
    bye
    -0.57
    POSITIVE LOGITS
    REAM
    0.85
    iour
    0.84
    agram
    0.80
    JECT
    0.77
    ceived
    0.77
     Bout
    0.75
    ãĥĩãĤ£
    0.74
    actionDate
    0.74
     Balloon
    0.74
     Animation
    0.72
    Act Density 0.039%

    No Known Activations