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

    Neuronpedia

    INDEX
    Explanations

    words related to doubt, uncertainty, or speculation

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions indicating a lack of belief or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.80
     Radiation
    -0.70
     tremend
    -0.70
     Penguin
    -0.68
    Reviewer
    -0.68
     Reloaded
    -0.67
     Passage
    -0.64
     Leopard
    -0.64
     rall
    -0.64
     submar
    -0.61
    POSITIVE LOGITS
    cha
    0.98
     necessarily
    0.87
    ople
    0.85
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.84
    otally
    0.81
    ween
    0.80
    Í
    0.80
     bother
    0.77
    ting
    0.77
     anymore
    0.76
    Act Density 0.068%

    No Known Activations