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

    Neuronpedia

    INDEX
    Explanations

    phrases related to objectives and goals

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

    ultimate outcome or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.57
    tology
    -0.52
     toalha
    -0.51
    IntoConstraints
    -0.49
     Geiſt
    -0.45
     thermique
    -0.45
    igil
    -0.44
     moldura
    -0.44
    Попис
    -0.44
    cerpts
    -0.44
    POSITIVE LOGITS
     Eventually
    0.74
    Eventually
    0.73
     eventually
    0.71
     eventual
    0.69
    eventually
    0.67
     Ultimately
    0.65
     ultimate
    0.64
     ultimately
    0.61
    Ultimately
    0.59
     uiteindelijk
    0.54
    Act Density 0.040%

    No Known Activations