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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "As" indicating conditions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ives
    -0.18
     evidenced
    -0.16
    etter
    -0.15
    eros
    -0.14
    igu
    -0.14
    è¹
    -0.14
    YNAM
    -0.14
     traction
    -0.14
    charge
    -0.14
    velop
    -0.14
    POSITIVE LOGITS
     luck
    0.17
    adian
    0.16
    lick
    0.15
    gard
    0.15
    Patch
    0.15
     clich
    0.15
    oÄŁ
    0.14
    bows
    0.14
    ared
    0.14
    addon
    0.14
    Act Density 0.055%

    No Known Activations