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

    Neuronpedia

    INDEX
    Explanations

    titles, citations, and other metadata in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ively
    -0.76
    entimes
    -0.75
     displeasure
    -0.73
     subsequ
    -0.71
     tremend
    -0.69
    ilant
    -0.69
     reapp
    -0.67
    mble
    -0.67
     committing
    -0.67
    omething
    -0.67
    POSITIVE LOGITS
     Various
    1.24
     None
    1.21
     Unknown
    1.20
     Cosponsors
    1.19
     TBA
    1.11
     Provided
    1.01
     TBD
    1.01
     http
    0.96
     https
    0.94
     ©
    0.91
    Act Density 0.153%

    No Known Activations