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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal growth and achievement

    oai_token-act-pair · gpt-3.5-turbo

    topics related to rights and procedural issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    building
    -0.56
    las
    -0.53
     Tarant
    -0.53
    cation
    -0.52
     Tropical
    -0.51
    erno
    -0.51
    rid
    -0.51
    launch
    -0.51
    sama
    -0.50
     Ange
    -0.50
    POSITIVE LOGITS
     themselves
    1.26
    selves
    1.01
     selves
    0.97
     careers
    0.91
     willingly
    0.81
     voluntarily
    0.79
     individually
    0.78
     their
    0.74
     incomes
    0.73
     elig
    0.70
    Act Density 1.022%

    No Known Activations