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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     job
    -0.40
     exp
    -0.39
     hal
    -0.38
     dep
    -0.37
     held
    -0.36
     prop
    -0.36
     put
    -0.35
     help
    -0.35
     &
    -0.35
     will
    -0.34
    POSITIVE LOGITS
     تانيه
    0.77
    AndEndTag
    0.75
     autorytatywna
    0.75
    herself
    0.73
     queſta
    0.71
    MigrationBuilder
    0.66
    AddTagHelper
    0.65
     myſelf
    0.65
    IntoConstraints
    0.64
     صوتيه
    0.64
    Act Density 0.367%

    No Known Activations