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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions or business settings

    oai_token-act-pair · gpt-3.5-turbo

    consistent use of punctuation in lists or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atives
    -0.85
    nces
    -0.84
    abouts
    -0.82
    eners
    -0.76
    lees
    -0.74
    ernels
    -0.74
    flows
    -0.71
    usions
    -0.69
    xes
    -0.68
     Accounts
    -0.68
    POSITIVE LOGITS
     preferably
    0.96
     regardless
    0.88
     or
    0.86
     albeit
    0.84
     poem
    0.83
     irrespective
    0.83
     etc
    0.82
     whereas
    0.81
     photograph
    0.80
     whether
    0.79
    Act Density 0.250%

    No Known Activations