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

    Neuronpedia

    INDEX
    Explanations

    hypothetical scenarios or possibilities based on specific conditions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to potential actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unison
    -0.80
     Consumers
    -0.74
    selves
    -0.72
     collective
    -0.69
    earch
    -0.67
     Gems
    -0.66
     affiliates
    -0.65
     Customers
    -0.65
     Policies
    -0.65
     scanners
    -0.64
    POSITIVE LOGITS
     himself
    1.25
     veto
    1.03
     assassinated
    0.98
     resign
    0.97
     Himself
    0.91
     cameo
    0.88
     succeed
    0.87
     be
    0.86
     become
    0.86
     personally
    0.85
    Act Density 0.469%

    No Known Activations