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

    Neuronpedia

    INDEX
    Explanations

    mindset-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to strategies, deals, and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Images
    -0.95
    inders
    -0.81
     Cosponsors
    -0.80
    ousands
    -0.78
    atars
    -0.77
    xes
    -0.75
    »Ĵ
    -0.74
    abytes
    -0.73
    姫
    -0.73
    features
    -0.73
    POSITIVE LOGITS
     thing
    1.37
     affair
    1.31
     situation
    1.13
     fest
    1.04
     issue
    1.04
     ploy
    1.04
    fest
    1.03
     joke
    1.00
     tactic
    1.00
     breaker
    0.97
    Act Density 0.457%

    No Known Activations