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

    Neuronpedia

    INDEX
    Explanations

    definitions or descriptions of various concepts or terms

    oai_token-act-pair · gpt-3.5-turbo

    definitions and descriptions of various types of violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.90
    ©¶æ¥µ
    -0.69
    senal
    -0.67
    DAQ
    -0.66
    Bridge
    -0.65
    daq
    -0.65
     Riyadh
    -0.65
    aukee
    -0.64
     theirs
    -0.64
     CentOS
    -0.64
    POSITIVE LOGITS
     oneself
    0.98
    eness
    0.86
    /(
    0.85
     uncond
    0.78
     resemblance
    0.76
    ensation
    0.74
     continuous
    0.74
    ness
    0.72
     irregular
    0.72
     abnormal
    0.69
    Act Density 0.764%

    No Known Activations