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

    Neuronpedia

    INDEX
    Explanations

    topics related to personal identity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.65
    <bos>
    -0.64
     which
    -0.60
    }\]
    -0.60
     ואת
    -0.58
    which
    -0.57
     والتي
    -0.56
     ()
    -0.55
    SizeF
    -0.55
     }(
    -0.55
    POSITIVE LOGITS
     FTW
    1.12
     ftw
    1.12
    ?
    1.03
     anyone
    0.91
     galore
    0.89
    ?!
    0.83
     indeed
    0.81
     =
    0.79
     huh
    0.78
    !
    0.75
    Act Density 0.626%

    No Known Activations