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

    Neuronpedia

    INDEX
    Explanations

    numerals and terms related to calculations or measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovel
    -0.18
    oup
    -0.16
    ï¸
    -0.15
     dress
    -0.15
    ̣
    -0.15
     Dress
    -0.15
    INET
    -0.15
    oma
    -0.14
    å¥ij
    -0.14
    onian
    -0.14
    POSITIVE LOGITS
    addock
    0.17
     mastur
    0.15
     masturbating
    0.15
     Hollow
    0.15
    riv
    0.14
    anst
    0.14
    .tell
    0.14
    illisecond
    0.13
    ship
    0.13
    -handle
    0.13
    Act Density 0.014%

    No Known Activations