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

    Neuronpedia

    INDEX
    Explanations

    phrases or statements related to cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the impact of actions and beliefs on outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.82
    etheless
    -0.72
    çĶ°
    -0.70
    oute
    -0.68
    WithNo
    -0.68
    luaj
    -0.67
    osate
    -0.65
    etz
    -0.63
    Ther
    -0.63
     Siberian
    -0.61
    POSITIVE LOGITS
     nurt
    0.80
     winners
    0.76
     paycheck
    0.74
     tangible
    0.74
     obey
    0.74
     entertain
    0.74
     smiles
    0.73
     deeds
    0.72
     measurable
    0.70
     rewards
    0.70
    Act Density 1.102%

    No Known Activations