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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making processes and their outcomes

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

    Follows "that," often indicating restatement or clarification

    np_acts-logits-general · gemini-2.0-flash

    that's exactly what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.58
     ModelExpression
    -0.50
    󠁴
    -0.49
    mbggenerated
    -0.45
     Feinde
    -0.45
    issors
    -0.44
    expandindo
    -0.44
    tonode
    -0.43
    Organisateur
    -0.43
    postsleuth
    -0.42
    POSITIVE LOGITS
     itulah
    1.21
    这就是
    1.05
     inilah
    1.03
    這就是
    0.95
     thats
    0.92
    これが
    0.90
     Именно
    0.89
     именно
    0.82
     Thats
    0.78
    Thats
    0.75
    Act Density 0.444%

    No Known Activations