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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, specifically the word "or"

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

    Alternatives to a condition or choice

    np_acts-logits-general · gemini-2.0-flash

    conjunction for alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.42
    SaveChanges
    -0.41
     <<<<<<<<<<<<<<
    -0.40
     honneur
    -0.37
    CFLAGS
    -0.36
     jeudi
    -0.35
    (©
    -0.33
     wszystkim
    -0.32
    DECISION
    -0.32
     Xinhua
    -0.32
    POSITIVE LOGITS
     otherwise
    0.74
     equivalently
    0.73
     else
    0.73
     even
    0.71
     bahkan
    0.69
     estekak
    0.68
     thậm
    0.68
     whatnot
    0.67
    干脆
    0.66
     perhaps
    0.66
    Act Density 0.251%

    No Known Activations