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

    Neuronpedia

    INDEX
    Explanations

    instances of liquid actions or states involving heat or temperature changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovel
    -0.15
    noho
    -0.15
    ModifiedDate
    -0.14
    825
    -0.14
     pob
    -0.14
    aha
    -0.14
     Crimes
    -0.14
    kara
    -0.14
    romatic
    -0.13
    992
    -0.13
    POSITIVE LOGITS
     gasoline
    0.26
     oil
    0.24
     ink
    0.24
     mud
    0.23
     paint
    0.23
     water
    0.23
     glue
    0.22
     mol
    0.22
     pitch
    0.21
     urine
    0.21
    Act Density 0.437%

    No Known Activations