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

    Neuronpedia

    INDEX
    Explanations

    phrases related to follow-ups or subsequent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اض
    -0.17
    _hdl
    -0.16
    /perl
    -0.16
    sortable
    -0.15
    mts
    -0.15
    anas
    -0.15
     пеÑĢен
    -0.15
    аÑĢаÑĤ
    -0.14
    URED
    -0.14
     Went
    -0.14
    POSITIVE LOGITS
    -on
    0.22
    -up
    0.21
    ship
    0.21
    -through
    0.18
    ships
    0.18
    -On
    0.17
    landa
    0.17
    -Up
    0.16
    [](
    0.15
    εÏĤ
    0.15
    Act Density 0.005%

    No Known Activations