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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adir
    -0.18
    LOAT
    -0.16
    iche
    -0.16
    opard
    -0.15
    Ñĥз
    -0.15
    aur
    -0.15
    LOB
    -0.15
    ardin
    -0.14
    etrize
    -0.14
    ILA
    -0.14
    POSITIVE LOGITS
    ients
    0.15
    lass
    0.15
     Uph
    0.15
     Economy
    0.14
     Reach
    0.14
    unsch
    0.14
    ei
    0.14
    uing
    0.14
    ued
    0.14
     Hava
    0.14
    Act Density 0.071%

    No Known Activations