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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ils
    -0.17
     preliminary
    -0.17
    antar
    -0.16
    allas
    -0.15
    Assertions
    -0.15
    illi
    -0.14
     Prel
    -0.14
    VRT
    -0.14
    monds
    -0.14
    agar
    -0.13
    POSITIVE LOGITS
    ableObject
    0.17
    ombat
    0.16
    upal
    0.16
    .scalablytyped
    0.16
    HAM
    0.15
     addCriterion
    0.15
    ynn
    0.14
    ingu
    0.14
     molec
    0.14
    arella
    0.14
    Act Density 0.090%

    No Known Activations