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

    Neuronpedia

    INDEX
    Explanations

    instances of vocal expressions or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vy
    -0.15
     glow
    -0.15
     Humb
    -0.14
     hum
    -0.14
    oor
    -0.14
    heart
    -0.13
     Hum
    -0.13
    isure
    -0.13
    zeit
    -0.13
     scope
    -0.13
    POSITIVE LOGITS
     louder
    0.20
     slogans
    0.20
     lou
    0.20
     praises
    0.18
    lou
    0.18
     luder
    0.17
     commands
    0.17
     encour
    0.16
     epith
    0.16
    raphics
    0.16
    Act Density 0.061%

    No Known Activations