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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and achievements

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

    comparison and relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     broadly
    -0.48
    IsPostBack
    -0.37
     substantially
    -0.35
     широко
    -0.35
    IPAC
    -0.34
    tvguidetime
    -0.34
     prominently
    -0.34
    значно
    -0.34
    misión
    -0.34
    眼下
    -0.33
    POSITIVE LOGITS
     nahilalakip
    0.81
     tartalomajánló
    0.68
    IsContent
    0.68
    Tikang
    0.62
     препратки
    0.61
    BeginContext
    0.60
    AndEndTag
    0.59
    exitRule
    0.57
     يتيمه
    0.55
    parsedMessage
    0.54
    Act Density 0.030%

    No Known Activations