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

    Neuronpedia

    INDEX
    Explanations

    clauses and structures associated with relative pronouns

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

    "which" or "who" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.71
    ourke
    -0.59
    lexikon
    -0.58
    withOpacity
    -0.58
     tslint
    -0.55
    ngdoc
    -0.54
     لينك
    -0.53
     veldig
    -0.53
    glBindBuffer
    -0.53
    SerializeField
    -0.52
    POSITIVE LOGITS
     vốn
    0.63
     wiederum
    0.63
     übrigens
    0.59
     szint
    0.59
    后者
    0.59
     البته
    0.58
     zugleich
    0.57
     admittedly
    0.57
     οποίο
    0.57
     freilich
    0.56
    Act Density 0.422%

    No Known Activations