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

    Neuronpedia

    INDEX
    Explanations

    references to smear campaigns and personal attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hurt
    -0.16
     recess
    -0.15
     Rand
    -0.14
     Burst
    -0.14
    ican
    -0.14
     Becker
    -0.13
    stor
    -0.13
     Unused
    -0.13
    946
    -0.13
     Boys
    -0.13
    POSITIVE LOGITS
     Pessoa
    0.17
     Fauc
    0.16
    .Css
    0.15
    frauen
    0.15
    anela
    0.14
    .persist
    0.14
    adele
    0.14
    ãĥ³ãĥij
    0.14
    irut
    0.14
    ATIO
    0.14
    Act Density 0.130%

    No Known Activations