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

    Neuronpedia

    INDEX
    Explanations

    references to "space" and its variations, indicating a focus on the concept of space in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.75
    )|\
    -0.74
    __":
    -0.73
    }],
    -0.71
    writeFieldEnd
    -0.71
     <<<<<<<<<<<<<<
    -0.71
    })*/
    -0.70
     défaite
    -0.69
     pleaſure
    -0.67
    }),
    -0.67
    POSITIVE LOGITS
     spaces
    1.17
     space
    1.15
     SPACE
    1.12
     Space
    1.11
    SPACE
    1.03
    Space
    1.01
    spaces
    1.00
     Spaces
    1.00
    Spaces
    0.99
    space
    0.94
    Act Density 0.171%

    No Known Activations