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

    Neuronpedia

    INDEX
    Explanations

    agreement and consensus in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģли
    -0.15
    åĪ¶
    -0.15
    754
    -0.14
    ìĭ¤
    -0.14
    fal
    -0.14
    cred
    -0.14
    fait
    -0.14
    instead
    -0.14
    _cred
    -0.14
    legen
    -0.14
    POSITIVE LOGITS
     sentiments
    0.18
     sentiment
    0.18
    adeon
    0.16
     statement
    0.16
    ongs
    0.16
     about
    0.15
     statements
    0.15
     Bail
    0.15
    .lt
    0.14
    .scalablytyped
    0.14
    Act Density 0.049%

    No Known Activations