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

    Neuronpedia

    INDEX
    Explanations

    references to television and telecommunications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sid
    -0.15
    ouro
    -0.15
    rud
    -0.15
    icol
    -0.15
    iful
    -0.15
     Gros
    -0.14
    ever
    -0.14
    enny
    -0.14
     Mess
    -0.14
    ska
    -0.14
    POSITIVE LOGITS
    vised
    0.24
    visions
    0.22
    medicine
    0.22
    phony
    0.21
    thon
    0.21
    graph
    0.20
    presence
    0.19
    communication
    0.19
    prompt
    0.19
    cÃŃ
    0.18
    Act Density 0.007%

    No Known Activations