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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating past experiences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĺħ
    -0.65
    ethy
    -0.64
     currently
    -0.61
    Soc
    -0.60
     presently
    -0.60
    ilings
    -0.58
    ãĥĺãĥ©
    -0.57
    *****
    -0.56
    current
    -0.56
     Currently
    -0.55
    POSITIVE LOGITS
     dealings
    0.97
     trouble
    0.84
     difficulty
    0.82
     success
    0.79
     plenty
    0.77
    oken
    0.76
     enough
    0.76
     undergone
    0.76
    drawn
    0.74
     recourse
    0.74
    Act Density 0.056%

    No Known Activations