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

    Neuronpedia

    INDEX
    Explanations

    words related to bankruptcy or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific regions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aug
    -0.71
     Proud
    -0.70
    adapt
    -0.69
    zos
    -0.67
    oux
    -0.63
    ija
    -0.62
    development
    -0.62
     Jennings
    -0.61
    ovember
    -0.60
     Reflex
    -0.59
    POSITIVE LOGITS
    anship
    0.84
    ħ
    0.79
    ¿½
    0.78
    planes
    0.72
    £ı
    0.70
     weap
    0.66
    ł
    0.65
    Ł
    0.64
    è¦ļéĨĴ
    0.64
    izons
    0.63
    Act Density 0.000%

    No Known Activations