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

    Neuronpedia

    INDEX
    Explanations

    phrases related to phone communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "call" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fiction
    -0.71
     Flavoring
    -0.69
     nonex
    -0.62
     embr
    -0.62
     bunny
    -0.61
     colon
    -0.60
    wikipedia
    -0.60
     Coat
    -0.58
     Kamp
    -0.58
     ILCS
    -0.57
    POSITIVE LOGITS
    igraph
    1.30
    backs
    1.26
    oused
    1.11
    ahan
    0.99
    ouses
    0.99
    outs
    0.97
    aghan
    0.93
    call
    0.87
    ign
    0.87
    calling
    0.85
    Act Density 0.046%

    No Known Activations