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

    Neuronpedia

    INDEX
    Explanations

    statements denoting impossibility or strong negation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb 'be' in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phabet
    -0.80
    erity
    -0.70
     Patrol
    -0.67
     flock
    -0.63
    culosis
    -0.62
     compose
    -0.61
     expire
    -0.60
    arcity
    -0.60
    rones
    -0.59
     fray
    -0.58
    POSITIVE LOGITS
     construed
    1.12
     traced
    1.06
     undone
    0.99
     avoided
    0.96
     reasoned
    0.95
     attributed
    0.95
     blamed
    0.92
     forgiven
    0.91
     interpreted
    0.90
     accommod
    0.89
    Act Density 0.087%

    No Known Activations