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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @stop
    -0.16
    ilos
    -0.15
    @dynamic
    -0.14
    áš
    -0.14
    tps
    -0.14
    @nate
    -0.14
     Kaplan
    -0.13
     chod
    -0.13
    adel
    -0.13
     obr
    -0.13
    POSITIVE LOGITS
    ixin
    0.16
    earer
    0.15
     Transparency
    0.14
    ankind
    0.13
    &r
    0.13
    ristol
    0.13
    ãĤ½ãĥ³
    0.13
    peak
    0.13
     consenting
    0.13
    readcr
    0.13
    Act Density 0.107%

    No Known Activations