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

    Neuronpedia

    INDEX
    Explanations

    elements related to software configuration and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifar
    -0.18
    IALOG
    -0.15
    aste
    -0.14
    ourg
    -0.13
    eltas
    -0.13
    ental
    -0.13
    Ïģε
    -0.13
    statt
    -0.13
    defs
    -0.13
    665
    -0.13
    POSITIVE LOGITS
    mode
    0.16
     force
    0.16
    force
    0.16
    inclu
    0.16
     Force
    0.16
     mode
    0.15
    amble
    0.15
     verbose
    0.15
     maximum
    0.15
     target
    0.15
    Act Density 0.182%

    No Known Activations