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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing necessity and assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.88
     AssemblyCompany
    -0.85
    principalTable
    -0.75
    CodeAttribute
    -0.68
     cdti
    -0.67
     Majefty
    -0.65
    principalColumn
    -0.65
     referenties
    -0.63
    ]`
    -0.62
    ++){
    -0.61
    POSITIVE LOGITS
     happen
    0.81
     happening
    0.79
     happens
    0.73
     happened
    0.68
     geschieht
    0.59
     occur
    0.58
    MenuView
    0.56
     occurs
    0.56
     done
    0.55
     avviene
    0.53
    Act Density 0.272%

    No Known Activations