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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong emotions and states of being

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to challenges and discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coh
    -0.65
     practition
    -0.63
     newcom
    -0.62
    ãĥ©ãĥ³
    -0.62
     sugg
    -0.61
     festive
    -0.61
    å¸
    -0.60
    ò
    -0.59
     jaw
    -0.59
     captcha
    -0.57
    POSITIVE LOGITS
    !--
    0.90
     nonetheless
    0.88
     anyways
    0.85
     anyway
    0.82
    hood
    0.81
    nesses
    0.79
     ain
    0.79
     itself
    0.78
    selves
    0.75
     alike
    0.75
    Act Density 0.609%

    No Known Activations