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

    Neuronpedia

    INDEX
    Explanations

    spans of text containing the word 'against'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the agricultural economy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hurricanes
    -0.74
    éĹĺ
    -0.69
     Bagg
    -0.68
     Elves
    -0.66
     Sorceress
    -0.63
     Bok
    -0.63
     Cors
    -0.59
     jeopardy
    -0.59
    upload
    -0.59
     Tarant
    -0.58
    POSITIVE LOGITS
    nostic
    1.48
    ressive
    1.19
    itating
    1.19
    rib
    1.14
    itates
    1.12
    grand
    1.11
    itate
    1.11
    eless
    1.08
    itations
    1.07
    ression
    1.06
    Act Density 0.019%

    No Known Activations