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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-term duration

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term duration or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILA
    -0.78
    IRO
    -0.69
    leck
    -0.68
    gency
    -0.68
    ECH
    -0.68
    ropolitan
    -0.66
    acity
    -0.65
    atche
    -0.65
    Reviewed
    -0.64
     Compass
    -0.64
    POSITIVE LOGITS
    itud
    1.04
    sword
    0.98
     ago
    0.94
     enough
    0.94
    leaf
    0.94
     overdue
    0.92
    lasting
    0.87
    term
    0.86
    itude
    0.85
     term
    0.85
    Act Density 0.049%

    No Known Activations