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

    Neuronpedia

    INDEX
    Explanations

    key adjectives describing important qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.78
    ImageContext
    -0.63
    @[+][
    -0.62
     coisa
    -0.60
     mía
    -0.59
    oneofs
    -0.59
    bootstrapcdn
    -0.59
     člov
    -0.57
     popolari
    -0.56
     pessoas
    -0.55
    POSITIVE LOGITS
     own
    0.89
     efforts
    0.84
     counterparts
    0.82
     ability
    0.82
     selves
    0.79
     contribution
    0.76
     foray
    0.76
    selves
    0.73
     abilities
    0.72
     arsenal
    0.72
    Act Density 0.383%

    No Known Activations