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

    Neuronpedia

    INDEX
    Explanations

    speculations about the future or potential outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or speculation about future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.73
    checked
    -0.72
     ceased
    -0.60
     waived
    -0.60
    noticed
    -0.58
    76561
    -0.58
     strengthens
    -0.58
     calmed
    -0.57
     didnt
    -0.57
    clerosis
    -0.56
    POSITIVE LOGITS
     be
    1.11
     entail
    1.07
     fare
    0.93
     achieve
    0.86
     accomplish
    0.85
     evolve
    0.81
     tolerate
    0.80
     react
    0.80
     consist
    0.79
     respond
    0.77
    Act Density 0.103%

    No Known Activations