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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful or destructive actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the word "blow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clause
    -0.73
     Brach
    -0.71
    heid
    -0.69
     Beir
    -0.69
    ript
    -0.69
    Gameplay
    -0.67
    ournal
    -0.64
    rete
    -0.61
    kson
    -0.61
    aho
    -0.60
    POSITIVE LOGITS
    job
    1.01
    jobs
    0.92
     apart
    0.89
     away
    0.89
    guns
    0.85
    pipe
    0.83
    out
    0.82
     kisses
    0.81
    hard
    0.81
     holes
    0.80
    Act Density 0.029%

    No Known Activations