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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating character experiences and emotional responses

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

    determiners followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.51
    Przypisy
    -0.41
    ftagPool
    -0.40
    PCell
    -0.39
    LError
    -0.39
     géant
    -0.38
     household
    -0.38
    Editorial
    -0.38
    ramientas
    -0.38
     δή
    -0.38
    POSITIVE LOGITS
    期刊论文
    0.49
    ंदीखरीदारी
    0.46
    ferrer
    0.41
     bittersweet
    0.40
    öst
    0.39
    +:+
    0.38
    EROUS
    0.38
     /\.(
    0.37
    medriver
    0.36
     deserving
    0.36
    Act Density 0.017%

    No Known Activations