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

    Neuronpedia

    INDEX
    Explanations

    expressions of subjective opinions or feelings

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

    expressions of preference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
    ſelves
    -0.68
    Autoritní
    -0.67
    IContainer
    -0.66
     nahilalakip
    -0.63
    parsedMessage
    -0.63
     Numerade
    -0.63
     ComVisible
    -0.63
     doInBackground
    -0.63
    Хьажоргаш
    -0.62
    POSITIVE LOGITS
    favorite
    0.46
     preference
    0.44
     favorite
    0.40
     preferred
    0.39
     lovely
    0.38
    preferred
    0.38
     admired
    0.37
    Vegeu
    0.36
    preference
    0.36
     admire
    0.36
    Act Density 0.032%

    No Known Activations