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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or approaching a specific event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direction or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Direct
    -0.63
     Perspective
    -0.61
    hare
    -0.60
    isco
    -0.60
    sworth
    -0.59
    venture
    -0.58
    rences
    -0.57
    achy
    -0.56
    caster
    -0.55
    hops
    -0.55
    POSITIVE LOGITS
    othal
    0.70
    âĶĢâĶĢâĶĢâĶĢ
    0.69
     date
    0.69
     investigate
    0.68
     pasture
    0.65
     defend
    0.64
    pload
    0.64
     compensate
    0.64
     baseline
    0.63
    asted
    0.62
    Act Density 0.069%

    No Known Activations