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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feelings and experiences about relationships and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etc
    -0.18
     etc
    -0.17
    âĢ¦↵↵
    -0.16
    ark
    -0.15
     ,↵↵
    -0.15
     ;↵
    -0.14
    ilogy
    -0.14
    ↵↵
    -0.13
    ationally
    -0.13
    ëĵ±
    -0.13
    POSITIVE LOGITS
     --
    0.32
     —
    0.29
     thanks
    0.22
     ...
    0.20
     ---
    0.20
     âĢķ
    0.20
     âĢ¦
    0.20
     âĶĢ
    0.19
    thanks
    0.19
     â
    0.15
    Act Density 1.118%

    No Known Activations