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

    Neuronpedia

    INDEX
    Explanations

    verbs related to demonstrating, revealing, or exhibiting actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "show" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assic
    -0.66
    nian
    -0.66
    etary
    -0.64
     retaining
    -0.63
    ilings
    -0.60
    kson
    -0.59
     compounded
    -0.59
    ataka
    -0.58
     proceeding
    -0.58
    agher
    -0.58
    POSITIVE LOGITS
    alter
    1.04
    biz
    1.00
    ered
    0.99
    manship
    0.94
    runners
    0.84
     Thumbnails
    0.76
    amy
    0.75
     signs
    0.74
    runner
    0.72
    heet
    0.72
    Act Density 0.048%

    No Known Activations