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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating favorable or unfortunate outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Fortunately and unfortunately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Akk
    -0.52
    ombic
    -0.51
     isle
    -0.51
    Télé
    -0.49
     ujednoznacz
    -0.49
    elis
    -0.48
    ryl
    -0.47
    eck
    -0.47
     Kulit
    -0.46
    isle
    -0.46
    POSITIVE LOGITS
     Fortunately
    1.33
    Fortunately
    1.32
     fortunately
    1.30
    fortunately
    1.24
     Unfortunately
    1.00
    unfortunately
    0.96
     unfortunately
    0.96
    Unfortunately
    0.95
    ureusement
    0.81
    unately
    0.80
    Act Density 0.004%

    No Known Activations