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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ιαÏĤ
    -0.15
    urable
    -0.15
    iff
    -0.15
    loo
    -0.14
    averse
    -0.14
    PCM
    -0.13
    urch
    -0.13
    htub
    -0.13
    avors
    -0.13
    avers
    -0.13
    POSITIVE LOGITS
    eliness
    0.21
    ania
    0.19
    renc
    0.19
    alker
    0.17
     Letter
    0.16
    esome
    0.16
    /right
    0.15
    åĦª
    0.15
    ardy
    0.15
    -fi
    0.15
    Act Density 0.009%

    No Known Activations