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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference a shared audience or community concerns

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

    for those who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sweise
    -0.39
    ždy
    -0.38
    pin
    -0.38
    ero
    -0.38
    ause
    -0.36
    pmc
    -0.35
     company
    -0.35
    toISOString
    -0.35
     Boa
    -0.35
     swarm
    -0.35
    POSITIVE LOGITS
    AnchorStyles
    0.52
     selera
    0.50
     linho
    0.45
     ſind
    0.45
     ſich
    0.45
    colgroup
    0.44
     Monfieur
    0.43
     chofe
    0.42
     paixão
    0.42
     préf
    0.42
    Act Density 0.022%

    No Known Activations