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

    Neuronpedia

    INDEX
    Explanations

    elements related to fictional fantasy and action themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]}>
    -0.53
    digkeit
    -0.49
    Sprintf
    -0.48
    }>
    -0.48
    ilibrium
    -0.47
     gefragt
    -0.47
    ArgumentParser
    -0.47
     atendido
    -0.46
    anément
    -0.46
    anken
    -0.45
    POSITIVE LOGITS
     prow
    0.88
     lurking
    0.87
     intent
    0.84
     stalking
    0.83
     targeting
    0.76
     attacking
    0.74
     wre
    0.72
     harassing
    0.69
     roaming
    0.69
     bent
    0.68
    Act Density 0.456%

    No Known Activations