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

    Neuronpedia

    INDEX
    Explanations

    references to virtual machine (VM) identifiers and their statuses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     stiefel
    -0.91
     jLabel
    -0.84
     Thackeray
    -0.79
     Clarion
    -0.78
     quæ
    -0.77
     Ith
    -0.77
     snippetHide
    -0.76
     Roskov
    -0.75
    RefNanny
    -0.75
    parseLong
    -0.75
    POSITIVE LOGITS
     vm
    1.23
     VM
    1.14
    vm
    1.11
     VMs
    0.96
    VM
    0.95
    vms
    0.76
    robat
    0.73
    machines
    0.68
     Post
    0.68
     Vm
    0.66
    Act Density 0.005%

    No Known Activations