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

    Neuronpedia

    INDEX
    Explanations

    negative or critical sentiments related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mie
    -0.16
    shaw
    -0.15
    ength
    -0.15
    amba
    -0.14
    eres
    -0.14
    aggio
    -0.14
     æ·
    -0.14
     สล
    -0.14
    ÄĽr
    -0.14
    orio
    -0.14
    POSITIVE LOGITS
    LastError
    0.15
    ستاÙĨ
    0.15
    .setOn
    0.14
     Vet
    0.13
     Merlin
    0.13
     etc
    0.13
     Heard
    0.13
    trie
    0.13
    rescia
    0.13
    hani
    0.13
    Act Density 0.330%

    No Known Activations