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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements related to time and distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     episode
    -0.16
    erdale
    -0.15
    upy
    -0.15
     zoekt
    -0.15
    cko
    -0.14
    gmt
    -0.14
    edd
    -0.14
     HR
    -0.14
    Ïĥη
    -0.14
    obil
    -0.13
    POSITIVE LOGITS
    score
    0.23
     score
    0.22
     Score
    0.20
    -score
    0.20
    SCORE
    0.20
     verst
    0.17
     lust
    0.17
     arp
    0.17
    ValuePair
    0.16
     SCORE
    0.16
    Act Density 0.148%

    No Known Activations