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

    Neuronpedia

    INDEX
    Explanations

    dates and related events

    oai_token-act-pair · gpt-3.5-turbo

    instances of an empty token or placeholder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regener
    -0.84
     accelerator
    -0.81
     governed
    -0.79
     cons
    -0.78
     larvae
    -0.78
     edged
    -0.76
     incremental
    -0.75
     endeav
    -0.75
     disciplines
    -0.74
     covenant
    -0.73
    POSITIVE LOGITS
    Advertisements
    1.50
    Looks
    1.46
    RIP
    1.39
    HAHAHAHA
    1.37
    Loading
    1.36
    Wow
    1.35
    Sorry
    1.33
    @
    1.32
    https
    1.31
    Translation
    1.31
    Act Density 0.113%

    No Known Activations