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

    Neuronpedia

    INDEX
    Explanations

    connections between verbs and their subjects or modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pii
    -0.17
     ABC
    -0.16
    623
    -0.16
    ouden
    -0.15
    ĵåIJį
    -0.15
    å³°
    -0.15
    roud
    -0.15
    oute
    -0.14
    olum
    -0.14
    ABC
    -0.14
    POSITIVE LOGITS
    ughs
    0.17
    ernen
    0.16
    izik
    0.15
    áÄį
    0.15
    plorer
    0.15
    cci
    0.15
    enis
    0.15
    engkap
    0.14
     Plug
    0.14
    angu
    0.14
    Act Density 0.001%

    No Known Activations