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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or change, especially involving removal or elimination

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of removing or eliminating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.78
    ebus
    -0.73
     Dragonbound
    -0.73
    ilant
    -0.72
    CLA
    -0.71
    company
    -0.70
    ny
    -0.70
    NING
    -0.69
    step
    -0.67
    translation
    -0.66
    POSITIVE LOGITS
     unwanted
    1.18
     unnecessary
    1.15
     obstacles
    1.06
     offending
    1.01
     redundant
    1.01
     traces
    0.99
     superflu
    0.98
     objectionable
    0.97
     troublesome
    0.95
     pesky
    0.95
    Act Density 0.106%

    No Known Activations