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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .sb
    -0.16
    olla
    -0.16
    wit
    -0.15
     пÑĢим
    -0.15
    oeff
    -0.15
     Carlton
    -0.15
     prm
    -0.14
    ÅĽcie
    -0.13
    ätz
    -0.13
    ıs
    -0.13
    POSITIVE LOGITS
    URNS
    0.14
    bern
    0.14
    ãĥ¼ãĥ³
    0.14
    å¹³æĪIJ
    0.14
    ofire
    0.13
    MX
    0.13
    _BU
    0.13
    quest
    0.13
    .fac
    0.13
    ãģĤãģ£ãģŁ
    0.13
    Act Density 0.026%

    No Known Activations