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

    Neuronpedia

    INDEX
    Explanations

    the word "Parents" and related mentions in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to parents and their involvement or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.94
    ocl
    -0.72
    ACTED
    -0.64
    icity
    -0.63
     HRC
    -0.61
     Pike
    -0.61
    atility
    -0.61
     executions
    -0.61
     Bowling
    -0.60
     Antar
    -0.60
    POSITIVE LOGITS
    hetical
    1.30
    hesis
    1.21
    heses
    1.08
    hetically
    1.02
    parents
    0.98
    Parents
    0.87
    hes
    0.81
    hood
    0.80
    chool
    0.75
     Parents
    0.75
    Act Density 0.029%

    No Known Activations