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

    Neuronpedia

    INDEX
    Explanations

    phrases related to military actions or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses indicating a negative or adverse condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preference
    -0.72
    opher
    -0.69
     suspic
    -0.69
     compens
    -0.67
     metic
    -0.67
    agra
    -0.67
    asketball
    -0.67
     manip
    -0.66
     pride
    -0.65
     sore
    -0.65
    POSITIVE LOGITS
    _-
    1.51
    âĢ¢âĢ¢
    0.94
    =-=-=-=-
    0.92
    ––
    0.88
    /-
    0.87
    âĸº
    0.87
    webkit
    0.87
     [|
    0.78
     Advertisement
    0.76
    including
    0.75
    Act Density 0.058%

    No Known Activations