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

    Neuronpedia

    INDEX
    Explanations

    numerical values or statistics related to products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tank
    -0.06
     Ones
    -0.06
     silver
    -0.06
     Latin
    -0.06
     tank
    -0.06
    ank
    -0.06
    ulist
    -0.06
     ap
    -0.06
     ham
    -0.05
    aber
    -0.05
    POSITIVE LOGITS
    opsy
    0.08
    eor
    0.08
     Unsigned
    0.07
     privilege
    0.07
    éģĬ
    0.07
    priv
    0.07
    ÑĭÑĪ
    0.07
    imson
    0.07
    ewise
    0.07
    ivas
    0.07
    Act Density 0.061%

    No Known Activations