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

    Neuronpedia

    INDEX
    Explanations

    references to the letter "F" followed by a single character or word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'F' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.73
     Aether
    -0.67
     Reborn
    -0.66
     Twain
    -0.65
     Hole
    -0.65
     Conquest
    -0.64
     Sapphire
    -0.64
     Hades
    -0.64
     Miko
    -0.63
     mater
    -0.63
    POSITIVE LOGITS
    ortun
    1.29
    ocused
    1.27
    ortunate
    1.22
    ocusing
    1.22
    ruits
    1.21
    avour
    1.21
    ertility
    1.18
    reet
    1.15
    OUND
    1.13
    AST
    1.13
    Act Density 0.058%

    No Known Activations