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

    Neuronpedia

    INDEX
    Explanations

    words related to political or administrative contexts

    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
    -0.74
    manship
    -0.65
     Boone
    -0.64
     clipboard
    -0.63
     Aether
    -0.63
     Miko
    -0.63
     Kop
    -0.62
     tackles
    -0.62
     Boll
    -0.61
    uyomi
    -0.61
    POSITIVE LOGITS
    rozen
    1.28
    avorable
    1.19
    ertility
    1.17
    requently
    1.16
    ocusing
    1.16
    ruits
    1.15
    avour
    1.15
    ocused
    1.13
    amiliar
    1.12
    rost
    1.11
    Act Density 0.036%

    No Known Activations