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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or likelihood

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

    I will do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Factbook
    -0.48
    ffilm
    -0.46
    ostante
    -0.45
     שוליים
    -0.44
    detectChanges
    -0.43
     hjel
    -0.43
     BoxFit
    -0.43
     policymakers
    -0.43
    stateMutability
    -0.42
     utveckling
    -0.42
    POSITIVE LOGITS
     myſelf
    0.55
    Myself
    0.48
     Rostock
    0.47
     myself
    0.46
     loosing
    0.44
     I
    0.43
     Myself
    0.43
     regret
    0.42
    myself
    0.42
     repent
    0.42
    Act Density 0.026%

    No Known Activations