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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the process of releasing or launching something

    oai_token-act-pair · gpt-3.5-turbo

    actions and events related to the release or progression of media and rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.90
     advoc
    -0.66
    guyen
    -0.62
     opio
    -0.61
     shortcuts
    -0.59
    paralle
    -0.57
    ibur
    -0.57
     streng
    -0.56
     horm
    -0.54
     hurry
    -0.53
    POSITIVE LOGITS
    .[
    0.99
    .
    0.95
    .;
    0.90
    .","
    0.89
    .:
    0.87
    ;
    0.84
     ().
    0.84
    !.
    0.84
    .$
    0.81
    .*
    0.79
    Act Density 0.302%

    No Known Activations