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

    Neuronpedia

    INDEX
    Explanations

    metrics and discussions around success measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wart
    -0.15
     Bounty
    -0.15
    claimer
    -0.15
    oot
    -0.14
    lingen
    -0.14
    ôme
    -0.14
    inci
    -0.14
    warts
    -0.14
    imizer
    -0.14
    ãĤ¤ãĥ¤
    -0.13
    POSITIVE LOGITS
     measures
    0.18
     Measures
    0.18
     metrics
    0.15
    metrics
    0.15
     surface
    0.14
     measure
    0.14
    lech
    0.14
     lep
    0.14
    ì§ij
    0.14
    ardash
    0.14
    Act Density 0.146%

    No Known Activations