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

    Neuronpedia

    INDEX
    Explanations

    mentions of parameters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.19
    atel
    -0.18
    ress
    -0.17
    ear
    -0.16
    eyi
    -0.16
    arken
    -0.16
    ermann
    -0.16
    quiv
    -0.15
    elier
    -0.15
    arga
    -0.15
    POSITIVE LOGITS
    ized
    0.28
    etrize
    0.27
    ater
    0.26
    etric
    0.26
    etr
    0.25
    ization
    0.23
    aters
    0.23
    ised
    0.23
    ter
    0.22
    ters
    0.21
    Act Density 0.031%

    No Known Activations