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

    Neuronpedia

    INDEX
    Explanations

    phrases related to detailed explanations or expansions of ideas

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

    elaboration and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.66
    zzleHttp
    -0.52
     AssemblyCulture
    -0.52
    Portail
    -0.49
    yntaxException
    -0.47
    InStock
    -0.47
    enderror
    -0.45
    IntoConstraints
    -0.45
     INTERESAR
    -0.44
    jspb
    -0.44
    POSITIVE LOGITS
     elaboration
    0.81
     explaining
    0.77
     explain
    0.77
    explain
    0.73
     elaborate
    0.73
     elabor
    0.72
    Elabor
    0.71
     explic
    0.69
     elaborated
    0.69
     explanation
    0.69
    Act Density 0.030%

    No Known Activations