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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Fre" followed by other letters

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Fre" and its variations across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOWN
    -0.73
    ividual
    -0.73
     Mori
    -0.72
    ONES
    -0.70
     Kai
    -0.68
     Adin
    -0.66
    rises
    -0.66
     Sapphire
    -0.65
     Beir
    -0.64
     Manip
    -0.64
    POSITIVE LOGITS
    eport
    0.98
    eway
    0.98
    ighters
    0.94
    emen
    0.93
    galitarian
    0.90
    ighter
    0.90
    estone
    0.89
    eland
    0.89
    elin
    0.86
    eman
    0.82
    Act Density 0.036%

    No Known Activations