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

    Neuronpedia

    INDEX
    Explanations

    public figures or authorities mentioned in news reports

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of individuals and officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.71
    Offline
    -0.68
     sail
    -0.66
     dear
    -0.65
     legends
    -0.64
     HMS
    -0.63
    Liter
    -0.63
     bandits
    -0.61
     bumper
    -0.60
     yacht
    -0.59
    POSITIVE LOGITS
     told
    0.94
     said
    0.91
    iott
    0.90
    meier
    0.87
     declined
    0.85
     acknowledged
    0.85
     oversaw
    0.85
    efe
    0.84
     briefed
    0.84
    etti
    0.83
    Act Density 0.286%

    No Known Activations