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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with raising awareness on various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ter
    -0.16
    ta
    -0.16
    иÑĩно
    -0.15
    aju
    -0.15
    TA
    -0.14
    ffer
    -0.14
    Ñĩно
    -0.14
    rib
    -0.14
    ize
    -0.14
    ting
    -0.14
    POSITIVE LOGITS
     eyebrows
    0.36
     awareness
    0.34
     hack
    0.28
     Awareness
    0.28
    aware
    0.27
     spirits
    0.27
     stakes
    0.27
     consciousness
    0.26
     funds
    0.26
     brows
    0.25
    Act Density 0.048%

    No Known Activations