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

    Neuronpedia

    INDEX
    Explanations

    statements indicating a condition or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    География
    -0.64
    itemBuilder
    -0.49
    rifuge
    -0.49
    มัน
    -0.49
     Bescheid
    -0.48
    which
    -0.47
    anyon
    -0.46
    ्य
    -0.45
     которое
    -0.44
    dorff
    -0.44
    POSITIVE LOGITS
     possible
    1.13
     impossible
    0.99
     raining
    0.97
     snowing
    0.93
    possible
    0.93
     obvious
    0.91
     unclear
    0.89
     clear
    0.89
     imperative
    0.87
     conceivable
    0.85
    Act Density 0.306%

    No Known Activations