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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating possession or states related to subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olah
    -0.16
    arking
    -0.15
    acam
    -0.15
     ÑģÑĩеÑĤ
    -0.15
     ÑģÑĩ
    -0.15
    मर
    -0.14
    iners
    -0.14
    oltip
    -0.14
    ucc
    -0.13
    pix
    -0.13
    POSITIVE LOGITS
     proven
    0.24
     momentum
    0.18
     proved
    0.16
     shown
    0.16
     one
    0.15
     already
    0.15
     plenty
    0.15
     demonstrated
    0.15
    éĽ²
    0.15
     prove
    0.14
    Act Density 0.057%

    No Known Activations