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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of proper nouns, specifically those starting with "Ch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plat
    -0.15
    átor
    -0.15
    618
    -0.15
    aria
    -0.14
     dep
    -0.14
    arts
    -0.14
    Nib
    -0.14
    plat
    -0.14
    067
    -0.14
    rom
    -0.14
    POSITIVE LOGITS
    atham
    0.22
    umph
    0.18
    apult
    0.17
    umont
    0.17
    âte
    0.16
    idding
    0.16
    omor
    0.16
    iang
    0.16
     Scalars
    0.15
    appa
    0.15
    Act Density 0.015%

    No Known Activations