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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to a particular figure or topic, potentially with a focus on a specific controversy surrounding them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the root "isl" and its variations related to legislation and dislocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.86
    plain
    -0.77
    lishing
    -0.77
    perty
    -0.72
    spect
    -0.71
    forth
    -0.71
    missions
    -0.71
    ris
    -0.69
    sic
    -0.69
    lio
    -0.68
    POSITIVE LOGITS
    ocated
    0.99
    ocate
    0.92
    aws
    0.89
    ocation
    0.89
    ocker
    0.88
    ative
    0.87
    iquid
    0.86
    apse
    0.86
    ikes
    0.82
    IGHT
    0.81
    Act Density 0.040%

    No Known Activations