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

    Neuronpedia

    INDEX
    Explanations

    terms related to volcanic activity and eruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Waterloo
    -0.15
     storm
    -0.14
     Sheldon
    -0.14
    ãĥŃãĥ³
    -0.14
    867
    -0.14
     ether
    -0.14
    unny
    -0.14
    Å¡t
    -0.14
    rost
    -0.14
     marrow
    -0.13
    POSITIVE LOGITS
     volcano
    0.30
     volcan
    0.30
     вÑĥл
    0.27
     volcanic
    0.25
     eruption
    0.24
     Vol
    0.23
    eru
    0.23
     ash
    0.22
     lava
    0.22
     eru
    0.22
    Act Density 0.047%

    No Known Activations