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

    Neuronpedia

    INDEX
    Explanations

    phrases related to finality or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing difficulty or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     condem
    -0.79
     conduc
    -0.74
     clitor
    -0.71
     Instr
    -0.71
    ulators
    -0.69
    raints
    -0.69
     hemor
    -0.68
     organisers
    -0.67
     aroused
    -0.67
     lapt
    -0.67
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.16
    ï¸ı
    1.06
    âĶĢâĶĢâĶĢâĶĢ
    0.98
    ×Ķ
    0.96
    âķIJâķIJ
    0.88
    λ
    0.85
    ----------------------------------------------------------------
    0.85
    ×ķ
    0.84
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.83
    ever
    0.82
    Act Density 0.233%

    No Known Activations