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

    Neuronpedia

    INDEX
    Explanations

    words related to options and choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Holmes
    -0.59
     vulner
    -0.57
     horizont
    -0.56
     Clancy
    -0.52
     Malone
    -0.52
     Goodman
    -0.51
    Leaks
    -0.51
     Petersen
    -0.50
     Hub
    -0.49
     Rover
    -0.49
    POSITIVE LOGITS
    Else
    1.29
    chard
    1.28
    acle
    1.14
    acles
    1.12
    acular
    1.12
    lando
    1.11
    chid
    1.08
    nery
    1.03
     else
    1.00
     alternatively
    0.98
    Act Density 0.036%

    No Known Activations