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

    Neuronpedia

    INDEX
    Explanations

    references to visual impressions and descriptions in relation to images and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shapes
    -0.18
    ackbar
    -0.17
     Shape
    -0.16
    æ½
    -0.15
    uite
    -0.15
    inent
    -0.15
     unp
    -0.14
    顯
    -0.14
    éĽª
    -0.14
     shapes
    -0.14
    POSITIVE LOGITS
     leave
    0.20
     send
    0.20
     make
    0.20
     rival
    0.19
     left
    0.18
     made
    0.18
    made
    0.17
     rivals
    0.17
     transport
    0.17
     Make
    0.17
    Act Density 0.113%

    No Known Activations