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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of leaves, such as paid leave and administrative leave

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various forms of leave from work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alist
    -0.83
    kered
    -0.82
    agonist
    -0.72
    gio
    -0.71
    ensen
    -0.71
     encount
    -0.69
    lisher
    -0.69
    rito
    -0.69
    ourke
    -0.68
    Reviewed
    -0.68
    POSITIVE LOGITS
    overs
    0.79
    away
    0.76
     leave
    0.73
    ings
    0.73
    wing
    0.70
     Leave
    0.69
    leave
    0.65
    uten
    0.63
     recipients
    0.62
    wich
    0.62
    Act Density 0.024%

    No Known Activations