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

    Neuronpedia

    INDEX
    Explanations

    connections between siblings and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bacteria
    -0.23
     biology
    -0.22
     β
    -0.21
     Biology
    -0.21
    (beta
    -0.19
    β
    -0.19
     batteries
    -0.18
     Bishop
    -0.18
     beta
    -0.18
     broadcasters
    -0.18
    POSITIVE LOGITS
    bum
    0.19
     worst
    0.17
    unbind
    0.17
     worse
    0.17
    Bit
    0.17
     Worst
    0.16
    aison
    0.16
    .unbind
    0.16
     unb
    0.16
     sisters
    0.15
    Act Density 0.137%

    No Known Activations