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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with the word 'then'

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases that imply causation or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toe
    -0.69
    brush
    -0.67
    assed
    -0.66
    ety
    -0.65
    chio
    -0.64
    ting
    -0.64
    ction
    -0.60
    ãĥ©ãĥ³
    -0.58
    ammy
    -0.57
    borgh
    -0.57
    POSITIVE LOGITS
     sshd
    0.84
    anski
    0.78
     Tens
    0.76
    Ļ½
    0.71
    orthy
    0.71
    etheless
    0.67
     guiActive
    0.67
     Inqu
    0.66
    forth
    0.65
     surely
    0.64
    Act Density 0.029%

    No Known Activations