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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and contrasting phrases in sentences

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

    not just, but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.44
    šinou
    -0.42
    jenost
    -0.41
    回事
    -0.37
    greif
    -0.37
    InitStruct
    -0.36
    gum
    -0.36
    corrhi
    -0.36
     zamanda
    -0.36
    ondissement
    -0.36
    POSITIVE LOGITS
    UrlResolution
    0.58
     nahilalakip
    0.53
     चीज़ों
    0.52
    Tikang
    0.50
    Geplaatst
    0.48
     bezeichneter
    0.46
    
    0.44
     esternos
    0.44
     pinulongan
    0.43
     Meksiku
    0.42
    Act Density 0.132%

    No Known Activations