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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the role or importance of various factors or elements in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.67
    IB
    -0.65
    ertation
    -0.61
     Shib
    -0.61
    ighting
    -0.59
    ortium
    -0.57
    ilings
    -0.57
    rians
    -0.56
    loss
    -0.56
    bey
    -0.55
    POSITIVE LOGITS
     havoc
    1.29
     roles
    0.99
     pivotal
    0.91
     important
    0.81
     catch
    0.79
     crucial
    0.78
     into
    0.78
    role
    0.77
     prominently
    0.77
     key
    0.77
    Act Density 0.035%

    No Known Activations