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

    Neuronpedia

    INDEX
    Explanations

    mentions of companies and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    remember
    -0.15
    esign
    -0.15
    otu
    -0.15
    ίÏĥ
    -0.15
    ожд
    -0.14
    dÃ¼ÄŁÃ¼
    -0.14
     Já
    -0.14
    PRETTY
    -0.13
    æĿ
    -0.13
    endid
    -0.13
    POSITIVE LOGITS
     plan
    0.51
     intend
    0.50
     plans
    0.48
     intends
    0.46
    plan
    0.41
     hope
    0.39
     intention
    0.39
     intentions
    0.38
     hopes
    0.38
    plans
    0.38
    Act Density 0.340%

    No Known Activations