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

    Neuronpedia

    INDEX
    Explanations

    adjectives or descriptions related to lengths of time

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term concepts or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leck
    -0.78
    illard
    -0.75
    IRO
    -0.75
    ILA
    -0.72
    atche
    -0.67
     Compass
    -0.66
    ECH
    -0.65
    Always
    -0.64
    unin
    -0.64
    ramid
    -0.63
    POSITIVE LOGITS
    itud
    1.28
     overdue
    1.07
    itudinal
    1.07
    lasting
    1.05
    sword
    1.05
     lasting
    1.00
     ago
    0.99
    itude
    0.98
     enough
    0.92
    leaf
    0.91
    Act Density 0.054%

    No Known Activations