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

    Neuronpedia

    INDEX
    Explanations

    references to water and its qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zbęd
    -0.93
    iibo
    -0.91
     mẽ
    -0.90
     myſelf
    -0.89
     ainfi
    -0.87
    BagConstraints
    -0.87
     Monfieur
    -0.86
     tartalomajánló
    -0.86
    jectures
    -0.83
    BeginContext
    -0.82
    POSITIVE LOGITS
     water
    1.78
     Water
    1.75
    Water
    1.71
    water
    1.63
     WATER
    1.55
    WATER
    1.47
     waters
    1.38
     Waters
    1.34
    Waters
    1.29
     Waterman
    1.27
    Act Density 0.051%

    No Known Activations