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

    Neuronpedia

    INDEX
    Explanations

    references to liquid substances and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enth
    -0.16
    agan
    -0.15
     Fluid
    -0.15
    kap
    -0.15
    žit
    -0.15
    uraa
    -0.15
    trak
    -0.15
    ÙĤر
    -0.15
    graded
    -0.14
    kh
    -0.14
    POSITIVE LOGITS
    ating
    0.24
    -solid
    0.23
    -phase
    0.23
    ity
    0.21
    ators
    0.21
    ation
    0.20
    -filled
    0.20
    ified
    0.19
     phase
    0.19
    ated
    0.19
    Act Density 0.014%

    No Known Activations