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

    Neuronpedia

    INDEX
    Explanations

    future-oriented verbs indicating certainty or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GED
    -0.17
    .Unity
    -0.17
    stery
    -0.16
    AREST
    -0.14
    bart
    -0.14
    екаÑĢ
    -0.14
     Woche
    -0.14
    HeaderCode
    -0.14
    амеÑĤ
    -0.14
    hift
    -0.14
    POSITIVE LOGITS
     interest
    0.22
     appeal
    0.21
     help
    0.20
     interests
    0.19
     appeals
    0.19
     appealed
    0.18
     suit
    0.17
    interest
    0.17
     familiar
    0.17
    berger
    0.16
    Act Density 0.092%

    No Known Activations