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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors that convey qualities and characteristics related to individuals and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pez
    -0.81
    ļéĨĴ
    -0.80
    igslist
    -0.79
    ICAN
    -0.78
    apse
    -0.76
    APS
    -0.76
    Ô
    -0.75
    uther
    -0.74
    Downloadha
    -0.74
    âĵĺ
    -0.74
    POSITIVE LOGITS
     maiden
    0.92
    hearted
    0.86
    ness
    0.84
     fellows
    0.84
    blooded
    0.83
     heart
    0.81
     deeds
    0.81
     lips
    0.81
    heart
    0.80
     shepherd
    0.79
    Act Density 0.670%

    No Known Activations