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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collective actions or decisions made by a group

    oai_token-act-pair · gpt-3.5-turbo

    instances of collective first-person pronouns and expressions of communal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.63
     Spec
    -0.63
     Publication
    -0.62
    cum
    -0.59
     Rowe
    -0.58
    ipal
    -0.57
     Deadline
    -0.56
    ãĥ¬
    -0.55
    imum
    -0.54
    wrapper
    -0.54
    POSITIVE LOGITS
    're
    1.18
     ourselves
    1.18
    akening
    1.16
     owe
    1.13
    've
    1.12
     shouldn
    1.04
     need
    1.04
    athered
    1.00
    asel
    1.00
     ought
    0.99
    Act Density 0.208%

    No Known Activations