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

    Neuronpedia

    INDEX
    Explanations

    references to electrical specifications and power connections for devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arith
    -0.16
    åijĨ
    -0.15
     bÄĥng
    -0.15
     convey
    -0.14
    infeld
    -0.14
    odos
    -0.14
    uze
    -0.13
     overwritten
    -0.13
     Subway
    -0.13
     dispatch
    -0.13
    POSITIVE LOGITS
     AC
    0.37
    AC
    0.31
     DC
    0.29
    .AC
    0.28
    交æµģ
    0.27
    dc
    0.26
    _AC
    0.26
     power
    0.26
    _DC
    0.26
     mains
    0.26
    Act Density 0.042%

    No Known Activations