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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beginnings or initiating actions

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

    Sentences or phrases starting with "start"

    np_acts-logits-general · gemini-2.0-flash

    the word "start"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ïse
    -0.66
    STERY
    -0.64
    로운
    -0.63
    /></
    -0.63
    Alpes
    -0.63
    honneur
    -0.63
     esternos
    -0.62
    autaire
    -0.62
    LEncoder
    -0.61
    хьтан
    -0.60
    POSITIVE LOGITS
     afresh
    0.87
     anew
    0.78
    START
    0.74
     START
    0.73
    ต้น
    0.69
     Starts
    0.68
     Start
    0.66
    starts
    0.65
    Starts
    0.64
     starts
    0.63
    Act Density 0.079%

    No Known Activations