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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     not
    -0.08
    nis
    -0.07
    ed
    -0.07
    ying
    -0.07
    not
    -0.06
    ase
    -0.06
    ual
    -0.06
    aksi
    -0.06
    toy
    -0.06
    oint
    -0.06
    POSITIVE LOGITS
     anymore
    0.08
    'gc
    0.08
    exact
    0.08
     necessarily
    0.07
    vetica
    0.07
    iband
    0.07
     Arbitrary
    0.07
    /upload
    0.06
    ’ta
    0.06
    lom
    0.06
    Act Density 0.021%

    No Known Activations