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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors aimed at individuals, particularly focusing on arrogance and incompetence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guien
    -0.60
     äm
    -0.56
    ]--;
    -0.55
     distinta
    -0.54
     ISNI
    -0.53
    Personendaten
    -0.51
     lenker
    -0.50
    endrait
    -0.50
     utafitiHapana
    -0.49
     médicas
    -0.48
    POSITIVE LOGITS
     idiot
    0.98
     asshole
    0.96
     bastard
    0.93
     prick
    0.91
     idiots
    0.91
     assholes
    0.91
     cunt
    0.91
     moron
    0.90
     douche
    0.89
     dumbass
    0.89
    Act Density 0.370%

    No Known Activations