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

    Neuronpedia

    INDEX
    Explanations

    references to existential questions about humanity and its actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iprot
    -0.59
    IntoConstraints
    -0.57
    +#+#
    -0.50
     يتيمه
    -0.48
    萌
    -0.45
    กลับ
    -0.44
    EndInit
    -0.43
     прош
    -0.42
    kirchen
    -0.41
     InputDecoration
    -0.41
    POSITIVE LOGITS
     humans
    0.54
     human
    0.51
     humanidad
    0.49
     Human
    0.48
     humaine
    0.47
     mankind
    0.47
     humains
    0.46
     humanas
    0.46
    human
    0.45
    Human
    0.45
    Act Density 0.274%

    No Known Activations