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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases using "as" or "like"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¾ãģŁ
    -0.19
    usercontent
    -0.17
    orte
    -0.14
    nik
    -0.13
    alis
    -0.13
    eno
    -0.13
    enen
    -0.13
    تÙĬÙĨ
    -0.13
    acity
    -0.13
    oster
    -0.12
    POSITIVE LOGITS
     those
    0.25
    ones
    0.23
     ours
    0.23
     ones
    0.22
     váºŃy
    0.18
     yours
    0.18
    those
    0.17
     напÑĢимеÑĢ
    0.16
     hers
    0.15
     unto
    0.15
    Act Density 0.081%

    No Known Activations