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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "to" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.84
    '])->
    -0.81
    ")->
    -0.71
     snippetHide
    -0.69
    ")"
    -0.69
    Kaynakça
    -0.68
    })->
    -0.65
    Amicalement
    -0.65
    %"),
    -0.64
    ]";
    -0.64
    POSITIVE LOGITS
    TestingModule
    0.57
    0
    0.56
    CreateMap
    0.56
    principalTable
    0.56
    2
    0.54
    1
    0.54
     too
    0.53
     faune
    0.53
    5
    0.53
    Afterwards
    0.53
    Act Density 0.219%

    No Known Activations