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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer security and technology

    oai_token-act-pair · gpt-3.5-turbo

    logical connectors and conjunctions related to comparisons and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouse
    -0.77
    ummer
    -0.77
    agara
    -0.73
     unborn
    -0.71
    ô
    -0.71
     therap
    -0.70
    stud
    -0.69
    jah
    -0.69
    wage
    -0.69
     dwelling
    -0.68
    POSITIVE LOGITS
     ITS
    0.97
     HIP
    0.95
     EPS
    0.89
     AZ
    0.86
     TT
    0.85
     IB
    0.85
     EF
    0.84
     UE
    0.84
     PF
    0.84
     QR
    0.83
    Act Density 0.315%

    No Known Activations