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

    Neuronpedia

    INDEX
    Explanations

    phrases related to connection or linking in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "connect" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheat
    -0.69
     Leaves
    -0.63
     spoil
    -0.63
    hra
    -0.61
    corn
    -0.60
     restraining
    -0.59
    Ħ¢
    -0.58
    gery
    -0.58
     concession
    -0.57
    fl
    -0.57
    POSITIVE LOGITS
    icut
    1.09
     dots
    0.99
    nect
    0.89
    Connect
    0.86
    links
    0.85
    ioned
    0.85
     Connect
    0.85
    ivity
    0.84
    anooga
    0.82
     connections
    0.81
    Act Density 0.029%

    No Known Activations