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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utin
    -0.18
    eward
    -0.17
    ward
    -0.17
    uten
    -0.16
    iger
    -0.16
    onn
    -0.15
    avr
    -0.15
    ron
    -0.15
    born
    -0.15
    SEMB
    -0.15
    POSITIVE LOGITS
    óż
    0.20
     pháºŃn
    0.18
    ifdef
    0.16
    çłģ
    0.16
    hood
    0.16
    erable
    0.15
     numberWith
    0.15
    arası
    0.14
    ERING
    0.14
    ismatic
    0.14
    Act Density 0.079%

    No Known Activations