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

    Neuronpedia

    INDEX
    Explanations

    conversations that involve familial relationships and parent-child dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     literally
    -0.59
    #+#
    -0.58
    vstack
    -0.57
    氏の
    -0.56
     damn
    -0.55
    toir
    -0.54
     essentially
    -0.48
    Literally
    -0.48
    氏が
    -0.48
     post
    -0.47
    POSITIVE LOGITS
     Jefus
    0.84
     Majefty
    0.78
     poffible
    0.78
    fois
    0.77
     itſelf
    0.77
     themſelves
    0.76
     ſeveral
    0.76
     spéciale
    0.75
     faſt
    0.74
     purpoſe
    0.73
    Act Density 0.107%

    No Known Activations