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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approximate measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ronym
    -0.17
    preneur
    -0.15
     absol
    -0.15
    unes
    -0.15
    amp
    -0.14
    inspace
    -0.14
    imits
    -0.14
    launcher
    -0.13
    perature
    -0.13
    edm
    -0.13
    POSITIVE LOGITS
    ledge
    0.19
    antine
    0.18
    lying
    0.16
    mente
    0.16
    oenix
    0.15
    oire
    0.15
    ç¿°
    0.15
    LY
    0.15
    itude
    0.15
    JP
    0.14
    Act Density 0.036%

    No Known Activations