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

    Neuronpedia

    INDEX
    Explanations

    instances of comma-separated lists or series in sentences

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

    Text fragments ending in prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    transfieras,findpost,endphp,Portale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ๆ
    -0.36
    ๆ
    -0.34
     sentimenti
    -0.32
     ...
    -0.31
     Nuestro
    -0.30
    jątk
    -0.29
     Ott
    -0.29
    matchCondition
    -0.29
     Beine
    -0.28
     many
    -0.28
    POSITIVE LOGITS
     transfieras
    0.83
    verwijspagina
    0.81
    findpost
    0.79
    endphp
    0.78
    Portale
    0.78
    SequentialGroup
    0.75
     AssemblyCulture
    0.75
    IsMutable
    0.75
    __*/
    0.75
     OMITBAD
    0.75
    Act Density 0.913%

    No Known Activations