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

    Neuronpedia

    INDEX
    Explanations

    references to various groups and their involvement or participation in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.16
    .scalablytyped
    -0.16
    deniz
    -0.16
     cigaret
    -0.15
    oref
    -0.14
    ocol
    -0.14
    efon
    -0.14
    ůl
    -0.14
    irie
    -0.14
    ết
    -0.14
    POSITIVE LOGITS
     can
    0.26
     should
    0.18
    åı¯ä»¥
    0.17
     must
    0.17
    can
    0.16
    218
    0.16
     receive
    0.16
    мож
    0.15
     Can
    0.15
     ent
    0.15
    Act Density 0.130%

    No Known Activations