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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucht
    -0.17
    vale
    -0.15
    ай
    -0.15
     Sab
    -0.14
     attempt
    -0.14
     Holmes
    -0.14
    iaux
    -0.14
    217
    -0.14
    abinet
    -0.14
     Sea
    -0.14
    POSITIVE LOGITS
    yre
    0.15
    nop
    0.15
    SHOT
    0.14
    lops
    0.14
    eld
    0.14
    lude
    0.14
     Cah
    0.13
     Naked
    0.13
    öh
    0.13
    elda
    0.13
    Act Density 0.061%

    No Known Activations