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

    Neuronpedia

    INDEX
    Explanations

    expressions and terms related to predictions and expectations about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "to" implying expectation

    np_acts-logits-general · gemini-2.0-flash

    future expectations and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
     tazas
    -0.44
    タジー
    -0.42
    ха
    -0.41
    isset
    -0.41
    chutz
    -0.41
    Then
    -0.40
     Dan
    -0.39
     causas
    -0.39
     supuesto
    -0.38
    POSITIVE LOGITS
    DockStyle
    1.09
     soon
    0.87
     prochain
    0.86
     eventually
    0.83
     eventual
    0.80
    出版年
    0.79
    Chham
    0.77
     Eventually
    0.77
    Eventually
    0.77
    soon
    0.75
    Act Density 0.349%

    No Known Activations