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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suggestions or recommendations

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

    look into or consider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.63
    httphttps
    -0.61
    testify
    -0.58
    parsedMessage
    -0.57
    setVerticalGroup
    -0.57
     betweenstory
    -0.56
     Италијани
    -0.55
    ientras
    -0.55
    ftagPool
    -0.53
     noDo
    -0.51
    POSITIVE LOGITS
     consideration
    0.62
     possibilities
    0.54
     alternatives
    0.47
     Consideration
    0.46
     considerations
    0.45
     options
    0.45
     consider
    0.44
     reconsider
    0.44
     consid
    0.43
     consideración
    0.43
    Act Density 0.024%

    No Known Activations