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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional and future tense verbs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uraa
    -0.17
    avour
    -0.15
    ardo
    -0.15
    ysi
    -0.14
    favor
    -0.14
    Injector
    -0.14
    ONO
    -0.14
    ivery
    -0.14
    POSIT
    -0.14
    iddy
    -0.14
    POSITIVE LOGITS
    kin
    0.16
    ria
    0.16
     harmon
    0.15
    .setViewport
    0.15
     sat
    0.14
    ream
    0.14
    onest
    0.14
    lot
    0.14
    ability
    0.14
    _rewrite
    0.13
    Act Density 0.030%

    No Known Activations