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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases that suggest uncertainty or complexity in opinions

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

    though although if not circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     médicas
    -0.46
     albeit
    -0.42
    albeit
    -0.41
    цездатний
    -0.41
     pédagogique
    -0.40
     közül
    -0.40
    Acab
    -0.40
     médicale
    -0.40
     Dennoch
    -0.39
     actualidad
    -0.39
    POSITIVE LOGITS
    ManagedBean
    0.50
    BeginContext
    0.48
     dAtA
    0.46
     SqlCommand
    0.45
    
    0.45
    findpost
    0.44
    UnusedPrivate
    0.43
    __((
    0.42
    FunctionFlags
    0.40
    elemField
    0.40
    Act Density 0.100%

    No Known Activations