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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making decisions or considering different options

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to weighing options or making evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.73
    employment
    -0.73
    ahime
    -0.67
    BLE
    -0.66
    cffffcc
    -0.65
    arak
    -0.64
     Osc
    -0.64
     Jobs
    -0.62
    \-
    -0.62
    ellen
    -0.62
    POSITIVE LOGITS
     weigh
    1.18
     weighing
    0.91
     weights
    0.89
    ighed
    0.88
     weighed
    0.84
     weighs
    0.79
     scales
    0.78
     corrid
    0.75
    iless
    0.75
    weights
    0.72
    Act Density 0.016%

    No Known Activations