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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or opinion

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

    Comes before opinions or statements

    np_acts-logits-general · gemini-2.0-flash

    expressing an opinion or making a statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -1.14
     estekak
    -1.03
    SharedDtor
    -0.98
     Италијани
    -0.96
     queſta
    -0.95
     Normdatei
    -0.93
     AssemblyCulture
    -0.91
    oneofs
    -0.91
     Taktlose
    -0.91
     betweenstory
    -0.91
    POSITIVE LOGITS
    ,
    0.40
     (
    0.38
    -
    0.36
     Verfügung
    0.36
     
    0.36
    _
    0.33
     the
    0.33
     of
    0.31
     used
    0.30
    (
    0.30
    Act Density 1.197%

    No Known Activations