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

    Neuronpedia

    INDEX
    Explanations

    terms related to prospective individuals or candidates in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reuse
    -0.16
    ennie
    -0.15
     Pred
    -0.15
     Herr
    -0.15
    InBackground
    -0.14
    keh
    -0.14
    kk
    -0.14
     decay
    -0.14
    nable
    -0.14
     Rip
    -0.14
    POSITIVE LOGITS
    gom
    0.16
    amba
    0.15
    atform
    0.15
     æ½
    0.15
    orque
    0.15
     Stamp
    0.14
    emouth
    0.14
    ű
    0.14
     SENSOR
    0.14
    .retry
    0.14
    Act Density 0.210%

    No Known Activations