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

    Neuronpedia

    INDEX
    Explanations

    references to family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wonderland
    -0.77
    WIND
    -0.74
     dwarf
    -0.72
    İĭ
    -0.70
     skirts
    -0.69
     concession
    -0.68
    dress
    -0.67
     hemp
    -0.66
     skirt
    -0.65
    ©¶æ
    -0.64
    POSITIVE LOGITS
    ilial
    1.76
    iliar
    1.60
    ilies
    1.24
    ili
    1.24
    ilar
    1.18
    ilia
    1.17
    ilitation
    1.17
    itsu
    1.12
    igl
    1.09
    iliate
    1.07
    Act Density 0.005%

    No Known Activations