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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and courtroom settings

    oai_token-act-pair · gpt-3.5-turbo

    references to fame or recognition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     capacitor
    -0.56
     loader
    -0.53
     instead
    -0.53
     launcher
    -0.51
     interchange
    -0.50
     ideally
    -0.50
     resistor
    -0.50
     Simpl
    -0.50
     converted
    -0.49
     nanop
    -0.49
    POSITIVE LOGITS
     endeavors
    0.69
    thood
    0.68
    pieces
    0.67
     events
    0.67
     tragedies
    0.66
    events
    0.66
     activities
    0.66
     outings
    0.65
     agendas
    0.65
     successes
    0.65
    Act Density 1.034%

    No Known Activations