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

    Neuronpedia

    INDEX
    Explanations

    phrases related to loss or separation

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships or interpersonal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VIDIA
    -0.54
     =================================
    -0.52
    laus
    -0.48
     Mell
    -0.47
     confir
    -0.46
     srfAttach
    -0.44
    ertodd
    -0.44
    ``
    -0.43
    Assembly
    -0.43
     Dhabi
    -0.43
    POSITIVE LOGITS
     badge
    0.60
    onto
    0.56
     itch
    0.51
    into
    0.51
    iddle
    0.50
     ASAP
    0.49
     salute
    0.49
     onto
    0.47
    thing
    0.47
     barrier
    0.47
    Act Density 2.358%

    No Known Activations