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

    Neuronpedia

    INDEX
    Explanations

    interrogative words related to location and inquiry

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

    the word "where" at the beginning of clauses indicating location or source.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     surla
    -0.69
    BeginContext
    -0.68
    TemporalType
    -0.65
     queſta
    -0.60
    AISSEE
    -0.60
    chism
    -0.60
    IUrlHelper
    -0.59
    Vorte
    -0.59
    extAlignment
    -0.58
    adaptiveStyles
    -0.57
    POSITIVE LOGITS
     they
    0.61
     exactly
    0.60
    exactly
    0.55
     else
    0.49
     he
    0.49
     именно
    0.49
     we
    0.47
     саме
    0.47
     it
    0.45
     EXACTLY
    0.45
    Act Density 0.217%

    No Known Activations