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

    Neuronpedia

    INDEX
    Explanations

    references to the beginning or start of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "opening" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.90
    cia
    -0.88
    ieving
    -0.87
    zin
    -0.77
    lean
    -0.75
    rome
    -0.73
    mel
    -0.71
    ka
    -0.71
    cles
    -0.69
    ided
    -0.69
    POSITIVE LOGITS
     ceremonies
    0.84
     Doors
    0.82
     opening
    0.82
     doors
    0.80
     salv
    0.75
     openings
    0.75
     weekend
    0.75
     reopen
    0.73
     Weekend
    0.73
     ceremony
    0.73
    Act Density 0.022%

    No Known Activations