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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Many" that suggest a large quantity or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illus
    -0.73
    OX
    -0.72
    ctrl
    -0.71
    ciation
    -0.67
    ieft
    -0.65
    uyomi
    -0.63
    oleon
    -0.61
    ISION
    -0.58
     Osiris
    -0.58
     ().
    -0.58
    POSITIVE LOGITS
     summers
    0.81
     readers
    0.79
     reviewers
    0.77
     times
    0.75
     critics
    0.71
     drafts
    0.71
     commentators
    0.71
     writers
    0.70
     observers
    0.70
     years
    0.70
    Act Density 0.080%

    No Known Activations