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

    Neuronpedia

    INDEX
    Explanations

    dates expressed as ordinal numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rhythm
    -0.70
    ItemTracker
    -0.69
    ombat
    -0.67
    MpServer
    -0.64
    natureconservancy
    -0.63
    VD
    -0.63
    UCT
    -0.60
    weekly
    -0.60
    zero
    -0.60
    EXP
    -0.59
    POSITIVE LOGITS
    dream
    0.98
     ago
    0.90
    lehem
    0.79
    theless
    0.79
     regret
    0.76
    lighting
    0.71
    oslov
    0.67
     after
    0.66
    elfth
    0.65
     later
    0.64
    Act Density 0.029%

    No Known Activations