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

    Neuronpedia

    INDEX
    Explanations

    phrases related to membership or inclusion in a group or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =Value
    -0.15
    lar
    -0.15
    zas
    -0.14
    elier
    -0.14
    lear
    -0.14
    æ´¾
    -0.14
    isp
    -0.14
    оÑģÑĮ
    -0.14
    .hm
    -0.14
    ulle
    -0.14
    POSITIVE LOGITS
    erras
    0.17
    ech
    0.15
     elements
    0.14
    mdat
    0.14
    errat
    0.14
    ANDLE
    0.14
    forth
    0.13
    objs
    0.13
    ilton
    0.13
    _userdata
    0.13
    Act Density 0.006%

    No Known Activations