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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or expressions related to negatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.72
     –
    -0.69
     --
    -0.66
    '--
    -0.65
    --
    -0.63
    ––
    -0.58
    — 
    -0.58
     �
    -0.56
    －
    -0.56
    ──
    -0.55
    POSITIVE LOGITS
    -(
    1.25
    -.
    1.10
    -)
    1.06
    -*
    1.01
    -]
    1.01
    Билгалдахарш
    0.98
    tvguidetime
    0.98
    -,
    0.96
    -!
    0.95
    -;
    0.93
    Act Density 0.153%

    No Known Activations