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

    Neuronpedia

    INDEX
    Explanations

    elements related to contrast and unexpected combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    á»ĥm
    -0.16
    isko
    -0.16
    aben
    -0.16
    MOTE
    -0.15
    'gc
    -0.15
    á»ĩn
    -0.15
     kvin
    -0.15
    /umd
    -0.15
    chartInstance
    -0.15
    POSITIVE LOGITS
    urt
    0.20
    ODB
    0.17
    Unexpected
    0.16
    unter
    0.15
     Pall
    0.15
     unexpected
    0.14
    ´
    0.14
     stere
    0.14
     normally
    0.14
     equ
    0.14
    Act Density 0.122%

    No Known Activations