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

    Neuronpedia

    INDEX
    Explanations

    phrases related to pursuing or targeting specific entities or objectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "after" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Released
    -0.75
    eller
    -0.74
    aez
    -0.71
    uph
    -0.70
    kept
    -0.68
    bell
    -0.68
    leave
    -0.68
    uten
    -0.66
    hes
    -0.65
    OVER
    -0.65
    POSITIVE LOGITS
     somebody
    0.70
    market
    0.65
    lain
    0.65
     him
    0.62
     whistleblowers
    0.61
     whichever
    0.60
     whoever
    0.59
     someone
    0.59
     something
    0.59
     fossil
    0.59
    Act Density 0.041%

    No Known Activations