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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tasks or actions that can be done or avoided without a specific requirement or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of doing something without additional requirement or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vald
    -0.73
     Christy
    -0.70
    nia
    -0.64
    undrum
    -0.63
    姫
    -0.63
    soon
    -0.60
    oret
    -0.60
     Delta
    -0.59
     Rodrigo
    -0.58
     Kinnikuman
    -0.57
    POSITIVE LOGITS
     oneself
    0.73
     necessarily
    0.66
     interruption
    0.64
    zzle
    0.63
    epad
    0.63
     explicitly
    0.62
     whatsoever
    0.61
     slightest
    0.60
     manually
    0.60
    endish
    0.59
    Act Density 0.088%

    No Known Activations