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

    Neuronpedia

    INDEX
    Explanations

    conditional and contextual phrases in discussions or arguments

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

    Punctuation marks followed by "and" or "the"

    np_acts-logits-general · gemini-2.0-flash

    pronoun or common word follows comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BrowserModule
    -0.55
     kaarangay
    -0.52
    пьютер
    -0.49
     Италијани
    -0.48
    Pls
    -0.48
     Comprometido
    -0.48
     betweenstory
    -0.47
     זאת
    -0.47
     Souhaitez
    -0.47
    horabuena
    -0.46
    POSITIVE LOGITS
     there
    1.22
     they
    1.02
    there
    0.90
     we
    0.89
     There
    0.74
     THERE
    0.72
    There
    0.71
     you
    0.69
     они
    0.61
    makeText
    0.60
    Act Density 0.459%

    No Known Activations