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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.24
     både
    -0.20
     rather
    -0.20
     even
    -0.20
     both
    -0.20
     and
    -0.19
    unj
    -0.17
     &
    -0.17
    either
    -0.17
     nothing
    -0.17
    POSITIVE LOGITS
     váºŃy
    0.19
    limited
    0.16
     بÙĦÚ©Ùĩ
    0.16
     limited
    0.16
     physical
    0.16
    withstanding
    0.15
     LIMITED
    0.15
     поÑĤомÑĥ
    0.15
    ÅĽcie
    0.15
    because
    0.15
    Act Density 0.048%

    No Known Activations