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

    Neuronpedia

    INDEX
    Explanations

    the word "all" in various contexts

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

    all or everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.62
    ValueStyle
    -0.57
    adaptiveStyles
    -0.57
     betweenstory
    -0.55
    rancy
    -0.55
    PostInfinity
    -0.55
    SourceChecksum
    -0.53
    ErrUnexpectedEOF
    -0.51
     Locus
    -0.50
    urne
    -0.50
    POSITIVE LOGITS
     all
    0.57
     everything
    0.52
     things
    0.51
     everyone
    0.50
     everybody
    0.50
     Semua
    0.50
     semua
    0.50
     Todas
    0.49
    Semua
    0.49
     все
    0.48
    Act Density 0.022%

    No Known Activations