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

    Neuronpedia

    INDEX
    Explanations

    mentions of fans or things related to fan experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to fans and their sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.70
    LY
    -0.67
     Coch
    -0.63
    EDIT
    -0.62
     Kaplan
    -0.62
    ENCE
    -0.61
    ateral
    -0.61
    Prosecut
    -0.58
     Proceedings
    -0.58
    tein
    -0.58
    POSITIVE LOGITS
     fans
    1.12
     Fans
    1.07
    Fans
    1.02
    atics
    0.93
    ervatives
    0.87
    atically
    0.87
    ervative
    0.87
    atical
    0.84
     rejoice
    0.84
    fan
    0.83
    Act Density 0.020%

    No Known Activations