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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clarity and evidence in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spisak
    -0.71
    IndentedString
    -0.58
    chenta
    -0.58
    OCCURRED
    -0.58
    ließlich
    -0.57
    новниш
    -0.56
    ειτουργ
    -0.55
    kömm
    -0.55
    ãy
    -0.55
    ipun
    -0.55
    POSITIVE LOGITS
     ascertain
    0.83
     ascertained
    0.80
     constater
    0.73
     revealed
    0.70
     reveal
    0.68
     ascertaining
    0.67
    revealed
    0.67
     ascer
    0.67
    detectChanges
    0.66
     पता
    0.65
    Act Density 0.569%

    No Known Activations