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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cab
    -0.16
     Morr
    -0.15
    Uint
    -0.15
    onga
    -0.15
    åįĴ
    -0.15
     cab
    -0.14
    aco
    -0.14
    Cab
    -0.14
    ono
    -0.14
    onis
    -0.14
    POSITIVE LOGITS
     Relief
    0.21
     relief
    0.21
     Disaster
    0.19
     disaster
    0.19
     vegetarian
    0.18
     Compass
    0.18
     sut
    0.17
     Bod
    0.17
     Buddhist
    0.17
     disasters
    0.17
    Act Density 0.000%

    No Known Activations