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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to animal horns, particularly rhino horns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of horns, particularly in relation to rhinos and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NCT
    -0.80
    âĸ¬
    -0.79
    ©¶æ
    -0.70
    ================================================================
    -0.70
     Tsarnaev
    -0.67
    TAIN
    -0.64
     ABE
    -0.63
    ################
    -0.62
    nex
    -0.62
    cedented
    -0.62
    POSITIVE LOGITS
     horns
    1.37
     horn
    1.24
    horn
    1.12
     trumpet
    0.90
    ofer
    0.90
    hovah
    0.89
     drums
    0.86
    pipe
    0.85
     guiActiveUn
    0.80
     guitars
    0.75
    Act Density 0.007%

    No Known Activations