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

    Neuronpedia

    INDEX
    Explanations

    sentences that emphasize experiences and feelings of assistance or satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    751
    -0.15
    htar
    -0.15
    ÙĬÙĩ
    -0.15
    ĸ
    -0.14
    fst
    -0.14
    THREAD
    -0.14
     si
    -0.14
    ohen
    -0.14
    ìŀ¥
    -0.14
     tape
    -0.13
    POSITIVE LOGITS
    ncia
    0.17
    ophon
    0.15
    enstein
    0.15
    -assets
    0.14
    avia
    0.14
    ÑĥнкÑĤ
    0.14
    orne
    0.14
    pong
    0.13
    omatic
    0.13
    à¥Ĥब
    0.13
    Act Density 0.267%

    No Known Activations