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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal documents and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.75
     sen
    -0.64
     ter
    -0.63
     pas
    -0.61
     or
    -0.60
     tra
    -0.59
     ab
    -0.59
    -
    -0.59
     pers
    -0.59
     her
    -0.58
    POSITIVE LOGITS
    ſelves
    1.05
     Theſe
    1.01
     Anſ
    0.97
    ſelf
    0.96
    tvguidetime
    0.93
    bibfield
    0.90
     Houſe
    0.90
     Diſ
    0.81
     Reſ
    0.81
     Jefus
    0.80
    Act Density 0.240%

    No Known Activations