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

    Neuronpedia

    INDEX
    Explanations

    ethnic and cultural references

    oai_token-act-pair · gpt-3.5-turbo

    references to groups related to terrorism or extremist organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     priv
    -0.61
     Speedway
    -0.60
     Malf
    -0.59
    ãĥ¼ãĥĨ
    -0.58
     Dise
    -0.57
     Fn
    -0.57
     Fol
    -0.56
    govtrack
    -0.56
     faculties
    -0.55
     inval
    -0.55
    POSITIVE LOGITS
    yz
    0.77
    ovsky
    0.74
    nik
    0.68
    anski
    0.66
    ofer
    0.65
    amed
    0.65
    iew
    0.65
    osate
    0.64
    orb
    0.64
    oz
    0.64
    Act Density 0.340%

    No Known Activations