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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing or bringing about something

    oai_token-act-pair · gpt-3.5-turbo

    references to various causes or reasons linked to different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     previews
    -0.78
     Preview
    -0.74
    ivo
    -0.65
    osa
    -0.64
    vis
    -0.64
    notes
    -0.64
     Integration
    -0.64
    back
    -0.63
     Wire
    -0.62
    packed
    -0.61
    POSITIVE LOGITS
     cause
    3.93
    cause
    2.98
     Cause
    2.88
     causes
    2.42
    Cause
    2.32
     Causes
    1.92
     causing
    1.50
     caus
    1.46
     causation
    1.35
     reason
    1.24
    Act Density 0.023%

    No Known Activations