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

    Neuronpedia

    INDEX
    Explanations

    relative clauses or phrases that refer to objects or subjects in a sentence

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

    that + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.56
    EndProject
    -0.56
     <<<<<<<<<<<<<<
    -0.56
    +#+#
    -0.55
     damn
    -0.54
     goddamn
    -0.53
     darn
    -0.52
    #+#
    -0.52
    IsMutable
    -0.51
     funny
    -0.50
    POSITIVE LOGITS
     amely
    0.54
     amelyek
    0.50
     którzy
    0.44
     których
    0.39
     során
    0.39
    異なります
    0.39
     lecz
    0.39
     technologies
    0.39
     auswählen
    0.38
     ktoré
    0.37
    Act Density 0.150%

    No Known Activations