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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "accept" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mingen
    -0.77
    rairie
    -0.67
    AdapterView
    -0.65
     sarebbero
    -0.61
     avrebbero
    -0.61
     AssemblyCulture
    -0.60
     devons
    -0.60
     defaultstate
    -0.59
     старости
    -0.59
    virons
    -0.58
    POSITIVE LOGITS
     accept
    3.50
     acceptance
    3.25
     Accept
    3.24
     accepting
    3.19
     accepts
    3.16
    accept
    3.07
     accepted
    3.04
     ACCEPT
    3.03
     Accepting
    3.02
    Accept
    2.98
    Act Density 0.067%

    No Known Activations