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

    Neuronpedia

    INDEX
    Explanations

    phrases related to working together or collective action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate collective actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.87
    ãĤ´ãĥ³
    -0.84
    algia
    -0.81
    emption
    -0.75
    ļéĨĴ
    -0.71
    ¤
    -0.71
    Ķ
    -0.70
    staking
    -0.68
    eah
    -0.67
    è£ħ
    -0.66
    POSITIVE LOGITS
     however
    1.01
     meanwhile
    0.80
     moreover
    0.77
     though
    0.72
     combatants
    0.64
     suffice
    0.60
     please
    0.60
     eh
    0.56
     we
    0.55
     surgeons
    0.54
    Act Density 0.252%

    No Known Activations