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

    Neuronpedia

    INDEX
    Explanations

    occurrences of certain punctuation marks and specific email addresses

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

    Comes after a period

    np_acts-logits-general · gemini-2.0-flash

    email signoffs and contact info

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Comunicação
    -0.52
     stratégique
    -0.49
     Atlántico
    -0.46
     Económica
    -0.45
     chaude
    -0.43
     Obras
    -0.42
     regiones
    -0.42
     artistique
    -0.42
     religieuse
    -0.42
     akcji
    -0.42
    POSITIVE LOGITS
    .$.
    0.59
    OGND
    0.58
    __.__
    0.58
     *.
    0.57
    \.
    0.57
     "*.
    0.55
     Infórmanos
    0.52
     /\.
    0.52
     <.
    0.52
    ngdoc
    0.51
    Act Density 0.680%

    No Known Activations