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

    Neuronpedia

    INDEX
    Explanations

    verb phrases indicating changes or conditions regarding availability or accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ials
    -0.18
    oth
    -0.15
    azen
    -0.15
    532
    -0.15
    YTE
    -0.14
    лада
    -0.14
     gag
    -0.14
    oller
    -0.14
    iac
    -0.14
    OTH
    -0.14
    POSITIVE LOGITS
    chas
    0.25
     traction
    0.24
     dice
    0.20
     underway
    0.20
     attention
    0.18
     away
    0.17
    dice
    0.17
    cha
    0.17
    away
    0.16
     Dice
    0.16
    Act Density 0.055%

    No Known Activations