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

    Neuronpedia

    INDEX
    Explanations

    comparative statements or phrases indicating differences and relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.69
     الرياضيه
    -0.68
     Chwiliwch
    -0.63
    StructEnd
    -0.61
    TagMode
    -0.60
     propOrder
    -0.60
    Jeografia
    -0.55
    hasia
    -0.54
    RTEE
    -0.53
     ModelExpression
    -0.52
    POSITIVE LOGITS
     favorably
    0.98
     favourably
    0.93
     against
    0.83
    against
    0.76
     apples
    0.70
     AGAINST
    0.66
    Against
    0.64
     Against
    0.64
     side
    0.59
     Apples
    0.55
    Act Density 0.231%

    No Known Activations