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

    Neuronpedia

    INDEX
    Explanations

    concepts related to bullying and harassment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppel
    -0.17
    adio
    -0.16
    æ§
    -0.14
    tet
    -0.14
     hypocrisy
    -0.14
    amine
    -0.14
     defe
    -0.13
     rij
    -0.13
    POSE
    -0.13
    820
    -0.13
    POSITIVE LOGITS
     bullying
    0.29
    bul
    0.27
     bully
    0.26
     Bul
    0.24
     harassment
    0.23
     bullied
    0.23
     harass
    0.22
     victim
    0.21
    victim
    0.20
     teasing
    0.19
    Act Density 0.038%

    No Known Activations