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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community engagement and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¤ij
    -0.15
    Capability
    -0.15
    tell
    -0.14
    pagen
    -0.14
    arsers
    -0.14
     originally
    -0.13
    าะ
    -0.13
    éra
    -0.13
     initially
    -0.13
     Cly
    -0.13
    POSITIVE LOGITS
     pride
    0.21
     value
    0.21
     recognizes
    0.21
    -commit
    0.19
     priority
    0.19
     commitment
    0.19
     aim
    0.19
     èĩ
    0.19
     believe
    0.18
     belief
    0.18
    Act Density 0.259%

    No Known Activations