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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight similarities and differences between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.71
     通販
    -0.62
    StructEnd
    -0.55
     pank
    -0.53
    forChild
    -0.51
     Cama
    -0.49
    циони
    -0.48
     isoto
    -0.48
     بيها
    -0.47
    MethodManager
    -0.47
    POSITIVE LOGITS
     similar
    0.74
     similarities
    0.74
    similar
    0.72
     SIMILAR
    0.71
     similarity
    0.69
     analogous
    0.69
     identical
    0.65
     ähnlichen
    0.63
     betweenstory
    0.62
     identically
    0.61
    Act Density 0.420%

    No Known Activations