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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal regret and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rosenstein
    -0.49
     backdrop
    -0.48
     Hof
    -0.48
     Eisen
    -0.48
    icist
    -0.48
     CLR
    -0.46
     Shots
    -0.44
     Shap
    -0.44
    aic
    -0.44
     Nation
    -0.44
    POSITIVE LOGITS
    ngth
    0.55
     owe
    0.54
     myself
    0.53
    interrupted
    0.51
    igi
    0.51
    oan
    0.51
     liking
    0.50
    SIGN
    0.50
     lose
    0.49
    illes
    0.49
    Act Density 0.751%

    No Known Activations